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

    numeric values or codes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hort
    -0.75
    icone
    -0.66
     Assange
    -0.61
    swick
    -0.61
     medd
    -0.59
    icol
    -0.59
    unity
    -0.59
     pastoral
    -0.58
    Reviewer
    -0.57
     Uri
    -0.57
    POSITIVE LOGITS
    Thirty
    1.03
    010
    0.85
    th
    0.85
    âĺħ
    0.82
    678
    0.80
    43
    0.80
    anging
    0.79
    42
    0.78
    0000
    0.75
    %-
    0.75
    Act Density 0.079%

    No Known Activations