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

    Neuronpedia

    INDEX
    Explanations

    terms associated with toxicity in a biological context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CrossRef
    -0.55
    ocene
    -0.54
    endpush
    -0.54
     vidare
    -0.53
     OnInit
    -0.52
    WindowConstants
    -0.52
     reemplazo
    -0.50
     fermés
    -0.49
     samodziel
    -0.49
     gård
    -0.49
    POSITIVE LOGITS
    toxicity
    3.03
     toxicity
    0.98
     pinulongan
    0.97
    enumi
    0.93
     Toxicity
    0.89
    󠁢
    0.88
    toxic
    0.87
    Toxicity
    0.78
    multicolumn
    0.77
     MainAxisSize
    0.76
    Act Density 0.022%

    No Known Activations