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

    Neuronpedia

    INDEX
    Explanations

    references to utility classes or methods in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    holm
    -0.17
    allon
    -0.15
    velt
    -0.15
    els
    -0.14
    asco
    -0.14
    ÙĤÙĤ
    -0.14
    038
    -0.14
    Fit
    -0.14
    ALES
    -0.14
     Osborne
    -0.13
    POSITIVE LOGITS
    ropa
    0.14
    год
    0.14
    plorer
    0.14
    oug
    0.14
    isateur
    0.14
    igar
    0.14
     Hao
    0.14
    комÑĥ
    0.14
     manip
    0.13
    acent
    0.13
    Act Density 0.017%

    No Known Activations