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

    Neuronpedia

    INDEX
    Explanations

    names of people or entities

    oai_token-act-pair · gpt-3.5-turbo

    names of people and references to conversations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Pg
    -0.63
    Wr
    -0.59
     bets
    -0.59
    ptions
    -0.57
     Cf
    -0.56
    =$
    -0.54
    bec
    -0.53
    }"
    -0.53
    IDS
    -0.53
     citation
    -0.53
    POSITIVE LOGITS
     about
    1.58
     ABOUT
    1.39
    about
    1.27
     About
    1.18
     regarding
    1.16
     concerning
    1.04
    About
    0.99
     privately
    0.85
     extensively
    0.83
     directly
    0.82
    Act Density 0.344%

    No Known Activations