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

    Neuronpedia

    INDEX
    Explanations

    terms associated with acceptance and rejection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    virons
    -0.68
    Korn
    -0.65
     старости
    -0.64
     Иль
    -0.64
     Potter
    -0.63
    mingen
    -0.63
    AdapterView
    -0.62
    highly
    -0.62
     avrebbero
    -0.61
     devriez
    -0.61
    POSITIVE LOGITS
     accept
    1.83
     Accept
    1.77
     accepts
    1.73
     acceptance
    1.67
     Accepting
    1.66
     ACCEPT
    1.65
     accepting
    1.64
     Acceptance
    1.60
     accepted
    1.58
    Accept
    1.58
    Act Density 0.081%

    No Known Activations