Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    elements of storytelling, including dramatic tension and emotional complexity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the end of this

    np_acts-logits-general · gemini-2.5-flash-lite

    sentence boundaries, especially the final word and adjacent punctuation at clause or sentence ends, and sometimes sentence-initial discourse markers.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Negative Logits
    UserScript
    -0.79
     ſei
    -0.76
    DockStyle
    -0.76
     autorytatywna
    -0.76
    <unused79>
    -0.75
    <unused52>
    -0.75
    [@BOS@]
    -0.75
    <unused41>
    -0.75
    <pad>
    -0.75
    <unused3>
    -0.75
    POSITIVE LOGITS
     sonunda
    0.28
    ↵↵
    0.26
    tal
    0.26
    me
    0.26
     Like
    0.25
    たとえば
    0.25
     like
    0.25
     ideally
    0.24
     treba
    0.24
    like
    0.23
    Act Density 0.143%

    No Known Activations