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

    Neuronpedia

    INDEX
    Explanations

    specific numerical values

    oai_token-act-pair · gpt-3.5-turbo

    instances of the number 98 in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    holders
    -0.89
    alien
    -0.81
    holder
    -0.80
    ItemImage
    -0.76
    eworld
    -0.75
    tarians
    -0.74
    NetMessage
    -0.73
    olas
    -0.69
    sworth
    -0.69
    ttp
    -0.67
    POSITIVE LOGITS
    coni
    0.80
    999
    0.78
    ption
    0.77
    lex
    0.75
    irement
    0.74
    152
    0.73
    ¢
    0.72
    808
    0.71
    765
    0.71
    98
    0.70
    Act Density 0.029%

    No Known Activations