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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific names, likely related to sports figures or other public figures

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns related to individuals and specific entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥĩãĤ£
    -0.89
    ffic
    -0.74
    âĢ¢âĢ¢
    -0.73
    ĸļ
    -0.73
     Wasteland
    -0.72
    loo
    -0.70
    CHAT
    -0.69
    uyomi
    -0.69
    IDA
    -0.66
     Riders
    -0.65
    POSITIVE LOGITS
    aced
    0.84
    ennes
    0.83
    nas
    0.83
    acia
    0.81
    emic
    0.77
     Alb
    0.76
    ens
    0.76
     Hodg
    0.75
    acy
    0.75
    nv
    0.75
    Act Density 0.019%

    No Known Activations