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

    Neuronpedia

    INDEX
    Explanations

    expressions of interest and desire in various contexts

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

    lack of interest

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     estekak
    -0.52
     geçir
    -0.48
     évêque
    -0.48
    erráneo
    -0.47
    HasForeignKey
    -0.47
    EDEFAULT
    -0.46
     VIDEOT
    -0.45
    orsese
    -0.45
     parseFrom
    -0.44
    principalColumn
    -0.44
    POSITIVE LOGITS
     unwilling
    0.48
     unwillingness
    0.41
    厭
    0.40
     reluctant
    0.38
     arc
    0.37
     reluctance
    0.36
    Referências
    0.35
    relu
    0.35
    不喜欢
    0.35
    willing
    0.34
    Act Density 0.051%

    No Known Activations