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

    Neuronpedia

    INDEX
    Explanations

    words related to software development or actions taken by developers

    oai_token-act-pair · gpt-3.5-turbo

    references to developers and development-related activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aukee
    -0.73
    Ĥİ
    -0.73
    zzi
    -0.73
    urn
    -0.72
    thur
    -0.68
    lla
    -0.67
    ll
    -0.66
    ibrary
    -0.66
    Ń·
    -0.65
    ysical
    -0.65
    POSITIVE LOGITS
    urally
    0.97
    paces
    0.76
     Developers
    0.75
     developer
    0.70
     developers
    0.69
    itatively
    0.68
    lisher
    0.68
    ency
    0.67
     accelerator
    0.67
     SDK
    0.66
    Act Density 0.027%

    No Known Activations