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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal feelings and emotional reactions

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

    Follows "makes me" or "makes you"

    np_acts-logits-general · gemini-2.0-flash

    pronoun followed by feeling or thought

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GeneratedCode
    -0.56
    ıt
    -0.51
     yourself
    -0.47
     sobie
    -0.47
     ourselves
    -0.47
    ذ
    -0.47
     令
    -0.46
    due
    -0.43
    辞典
    -0.42
    based
    -0.42
    POSITIVE LOGITS
    XmlAccessorType
    0.85
    ThroughAttribute
    0.80
     ModelExpression
    0.77
     rethink
    0.73
    ruptedException
    0.71
    حيان
    0.69
    scryfall
    0.66
    AnchorStyles
    0.66
    InitVars
    0.63
     &_
    0.62
    Act Density 0.172%

    No Known Activations