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

    Neuronpedia

    INDEX
    Explanations

    references to specific species or biological classifications

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

    specific words followed by another word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -1.24
     queſta
    -1.15
    <unused41>
    -1.13
    featureID
    -1.13
    <unused43>
    -1.13
    <pad>
    -1.13
    <unused17>
    -1.12
    <unused23>
    -1.12
    <unused8>
    -1.12
    [@BOS@]
    -1.12
    POSITIVE LOGITS
    The
    0.75
    ↵
    0.71
    I
    0.64
    You
    0.63
     
    0.63
    1
    0.62
     I
    0.60
    '
    0.60
    It
    0.60
    We
    0.59
    Act Density 0.000%

    No Known Activations