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

    Neuronpedia

    INDEX
    Explanations

    Unicode characters or codes

    oai_token-act-pair · gpt-3.5-turbo

    numerical values associated with dates and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ¤ãĥĪ
    -0.87
    ivities
    -0.81
    lier
    -0.74
    ivity
    -0.72
    OPLE
    -0.72
    ICLE
    -0.69
    icular
    -0.69
    ique
    -0.68
    cil
    -0.68
    hest
    -0.68
    POSITIVE LOGITS
     externalToEVAOnly
    0.98
    98
    0.82
    987
    0.81
    80
    0.78
    mph
    0.77
    989
    0.77
    pher
    0.74
    wark
    0.73
    myra
    0.72
    IOR
    0.70
    Act Density 0.146%

    No Known Activations