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

    Neuronpedia

    INDEX
    Explanations

    confidence-related words or phrases

    oai_token-act-pair · gpt-3.5-turbo

    terms related to confusion or uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    senal
    -0.76
    minecraft
    -0.73
    hao
    -0.71
    GG
    -0.68
    ©¶æ
    -0.68
    GY
    -0.68
    GET
    -0.67
     Wilde
    -0.67
    bye
    -0.66
     Kinnikuman
    -0.66
    POSITIVE LOGITS
    lict
    1.37
    licts
    1.35
    licted
    1.30
    irmation
    1.23
    erences
    1.13
    irms
    1.12
    luence
    1.12
    idential
    1.06
    irming
    1.06
    liction
    1.05
    Act Density 0.008%

    No Known Activations