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

    Neuronpedia

    INDEX
    Explanations

    references to financial penalties and consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ar
    -0.16
    111
    -0.15
    pg
    -0.15
     Eisen
    -0.15
    age
    -0.15
    benchmark
    -0.14
     Sa
    -0.14
     via
    -0.14
    pause
    -0.14
     w
    -0.14
    POSITIVE LOGITS
    mere
    0.17
    andle
    0.16
    ESCO
    0.15
    본
    0.15
    -san
    0.15
    åĸ
    0.15
    lashes
    0.14
    zek
    0.14
    deen
    0.14
    sume
    0.14
    Act Density 0.174%

    No Known Activations