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

    Neuronpedia

    INDEX
    Explanations

    numerical values

    oai_token-act-pair · gpt-3.5-turbo

    instances of the number "5" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hort
    -0.67
    opter
    -0.63
    swick
    -0.62
    icol
    -0.61
    icone
    -0.58
    xual
    -0.58
     Assange
    -0.58
    âĹ¼
    -0.57
    ensen
    -0.57
    perature
    -0.57
    POSITIVE LOGITS
    Thirty
    1.18
    âĺħ
    0.83
    th
    0.79
    678
    0.78
    anging
    0.78
    010
    0.77
    ths
    0.76
    43
    0.76
    teen
    0.75
    asted
    0.73
    Act Density 0.120%

    No Known Activations