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

    Neuronpedia

    INDEX
    Explanations

    specific instances or examples of something mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    phrases that reference specific cases or examples in a legal or analytical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kefeller
    -0.74
    elta
    -0.74
    urd
    -0.74
    rosso
    -0.73
    ruary
    -0.69
    irds
    -0.68
    arus
    -0.68
    autical
    -0.67
    ursday
    -0.67
    itionally
    -0.66
    POSITIVE LOGITS
    cases
    0.83
    mma
    0.75
     case
    0.74
    case
    0.72
     Canaver
    0.69
     cases
    0.69
     instance
    0.67
    DragonMagazine
    0.66
    verse
    0.64
     Case
    0.63
    Act Density 0.021%

    No Known Activations