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

    Neuronpedia

    INDEX
    Explanations

    mentions of authoritative reports or investigations

    oai_token-act-pair · gpt-3.5-turbo

    references to reports or statements from authorities or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apon
    -0.81
    obyl
    -0.80
    quit
    -0.80
    successfully
    -0.79
    bol
    -0.77
    artifacts
    -0.75
    abiding
    -0.74
    ardless
    -0.74
    ãĥİ
    -0.72
    akeru
    -0.69
    POSITIVE LOGITS
     spokesperson
    0.77
     tracker
    0.73
     vendor
    0.71
     Fortune
    0.70
     quoted
    0.69
     spokeswoman
    0.69
     spokesman
    0.68
     datas
    0.68
     synopsis
    0.67
     recru
    0.66
    Act Density 0.250%

    No Known Activations