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

    Neuronpedia

    INDEX
    Explanations

    discussions related to societal responses and perspectives on various issues

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

    hypothetical reactions and perceptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IsMutable
    -0.92
     kasarigan
    -0.86
    OGND
    -0.82
     AssemblyCulture
    -0.81
    ReusableCell
    -0.77
    Spolja
    -0.74
     snippetHide
    -0.73
    Ⴈ
    -0.73
    rungsseite
    -0.73
     geſch
    -0.71
    POSITIVE LOGITS
     different
    0.34
     after
    0.32
     when
    0.31
     war
    0.30
     what
    0.29
     War
    0.28
    /
    0.27
     
    0.27
     how
    0.26
     put
    0.26
    Act Density 0.251%

    No Known Activations