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

    Neuronpedia

    INDEX
    Explanations

    color-related terms

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly parentheses and their usage in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    worldly
    -0.64
    rosis
    -0.63
    asha
    -0.63
    ton
    -0.61
    rogen
    -0.61
    rogens
    -0.61
    TON
    -0.60
    ez
    -0.60
    Thumbnail
    -0.59
    hunt
    -0.58
    POSITIVE LOGITS
     meanwhile
    0.68
     namely
    0.67
     nevertheless
    0.66
    775
    0.65
     preferring
    0.63
     however
    0.63
    Aust
    0.62
     Flavoring
    0.62
    agascar
    0.61
     nonetheless
    0.59
    Act Density 0.057%

    No Known Activations