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

    Neuronpedia

    INDEX
    Explanations

    mentions related to media captions

    oai_token-act-pair · gpt-3.5-turbo

    references to media content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abouts
    -0.66
    ranch
    -0.65
    ta
    -0.65
    ŃĶ
    -0.64
     Salvador
    -0.64
    ãĤ¡
    -0.64
     Parenthood
    -0.63
    comes
    -0.63
    izontal
    -0.63
    atars
    -0.62
    POSITIVE LOGITS
    eval
    1.03
     outlets
    0.95
     playback
    0.86
    conference
    0.81
     outlet
    0.81
     conference
    0.80
     mog
    0.77
    wiki
    0.74
    Buzz
    0.73
     plurality
    0.73
    Act Density 0.027%

    No Known Activations