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

    Neuronpedia

    INDEX
    Explanations

    names of well-known media personalities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific media personalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ramid
    -0.84
    axter
    -0.72
    esthetic
    -0.70
    oan
    -0.68
    ?????
    -0.68
    ipper
    -0.68
    oa
    -0.68
    boarding
    -0.66
    board
    -0.66
    joining
    -0.64
    POSITIVE LOGITS
     Colbert
    1.13
     pauses
    0.79
    vill
    0.74
    wald
    0.73
    opard
    0.71
     Fallon
    0.71
     stares
    0.68
    anos
    0.65
    ipher
    0.65
     Burnett
    0.63
    Act Density 0.005%

    No Known Activations