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

    Neuronpedia

    INDEX
    Explanations

    legal terms and phrases

    oai_token-act-pair · gpt-3.5-turbo

    instances of numerical values that indicate severity or urgency in a statement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stellar
    -0.83
    argon
    -0.77
    renheit
    -0.74
    ensibly
    -0.69
    tion
    -0.68
    minist
    -0.68
    irtual
    -0.67
    ãĥŃ
    -0.64
     Stellar
    -0.63
    anium
    -0.63
    POSITIVE LOGITS
     Hatt
    0.74
     Franch
    0.71
     Jol
    0.68
    sonian
    0.65
     condem
    0.65
     gol
    0.63
     REUTERS
    0.62
    ↵
    0.62
     sinners
    0.61
     SPORTS
    0.59
    Act Density 0.157%

    No Known Activations