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

    Neuronpedia

    INDEX
    Explanations

    versions of software or operating systems

    oai_token-act-pair · gpt-3.5-turbo

    numerical values associated with software versions or updates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ersen
    -0.65
     affili
    -0.58
     decimal
    -0.57
    ulic
    -0.56
     plural
    -0.55
     caster
    -0.53
     solic
    -0.52
    quist
    -0.52
     correspondence
    -0.52
    rosse
    -0.52
    POSITIVE LOGITS
    0
    0.83
    apple
    0.77
    MX
    0.72
    dll
    0.69
    Downloadha
    0.65
    5
    0.65
    1
    0.64
    iOS
    0.63
    ubi
    0.61
    041
    0.61
    Act Density 0.051%

    No Known Activations