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

    Neuronpedia

    INDEX
    Explanations

    phrases that express negation or uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     IST
    -0.47
    SerializeField
    -0.42
    FormsModule
    -0.40
     ESM
    -0.38
    selle
    -0.38
    PreAuthorize
    -0.38
     Unterneh
    -0.38
    isfile
    -0.36
    EOF
    -0.36
    ESM
    -0.36
    POSITIVE LOGITS
    aucun
    0.65
     ſmall
    0.64
     leaſt
    0.64
    ंदीखरीदारी
    0.63
    AutoField
    0.61
     greateſt
    0.61
     whoſe
    0.59
    aucune
    0.59
     Houſe
    0.58
     leſs
    0.58
    Act Density 0.127%

    No Known Activations