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

    Neuronpedia

    INDEX
    Explanations

    initials of individuals or organizations

    oai_token-act-pair · gpt-3.5-turbo

    short phrases or abbreviations appearing in a sequence that may signify titles or headings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    theless
    -0.88
     Izan
    -0.61
    caps
    -0.59
    tnc
    -0.58
     scept
    -0.57
     unlikely
    -0.56
     heck
    -0.56
     whisk
    -0.55
    ItemTracker
    -0.54
    source
    -0.54
    POSITIVE LOGITS
    .,
    1.83
    .?
    1.62
    .:
    1.53
    .;
    1.47
    .,"
    1.45
    ./
    1.36
    .—
    1.23
    .),
    1.16
    .-
    1.15
    orporated
    1.01
    Act Density 0.071%

    No Known Activations