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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing the purpose or intended outcome of actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     consci
    -0.47
     Nowak
    -0.47
     itſelf
    -0.47
     victime
    -0.46
     catena
    -0.44
     trama
    -0.43
     bottes
    -0.42
     roue
    -0.42
     straff
    -0.42
     Clegg
    -0.41
    POSITIVE LOGITS
     for
    1.34
     For
    1.21
    for
    1.20
     FOR
    1.14
    For
    1.14
    สำหรับ
    1.08
     für
    1.05
     voor
    1.05
     untuk
    1.04
     для
    1.03
    Act Density 0.790%

    No Known Activations