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

    Neuronpedia

    INDEX
    Explanations

    instances of negation or disbelief in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     émotion
    -0.63
    lamó
    -0.63
    ierno
    -0.60
     médicaux
    -0.60
     dries
    -0.60
    )]:
    -0.59
     andato
    -0.58
     mourut
    -0.58
     armis
    -0.57
    sigs
    -0.57
    POSITIVE LOGITS
    częściej
    0.80
     have
    0.75
    ledem
    0.72
     lượt
    0.68
     be
    0.68
    又能
    0.68
    verläs
    0.67
    mappedBy
    0.65
    vatar
    0.65
    redge
    0.65
    Act Density 0.173%

    No Known Activations