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

    Neuronpedia

    INDEX
    Explanations

    elements that evoke emotional depth and warmth in storytelling

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

    positive emotions and virtue

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    addCriterion
    -0.36
    adaptiveStyles
    -0.32
     zasi
    -0.30
    AndEndTag
    -0.30
    IBOutlet
    -0.29
     themselves
    -0.29
     deseas
    -0.28
    matur
    -0.28
     trained
    -0.27
     typelib
    -0.27
    POSITIVE LOGITS
    DockStyle
    0.65
     kasarigan
    0.63
     Italijanski
    0.60
    CppCodeGen
    0.57
    __]
    0.56
     palliative
    0.55
    divarius
    0.55
    <unused41>
    0.55
    <pad>
    0.54
    [@BOS@]
    0.54
    Act Density 0.150%

    No Known Activations