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

    Neuronpedia

    INDEX
    Explanations

    references to famous people's names

    oai_token-act-pair · gpt-3.5-turbo

    references to notable individuals and names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ename
    -0.95
    icka
    -0.93
    eness
    -0.93
    onia
    -0.93
    orage
    -0.89
    rait
    -0.89
    opher
    -0.88
    igating
    -0.88
    ronic
    -0.86
    ary
    -0.86
    POSITIVE LOGITS
     Hebdo
    0.87
     Circus
    0.68
    balls
    0.66
     Temper
    0.66
    nton
    0.65
    lihood
    0.65
     Speedway
    0.64
    Frames
    0.63
     Cricket
    0.62
     Scouts
    0.62
    Act Density 0.066%

    No Known Activations