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

    Neuronpedia

    INDEX
    Explanations

    examples illustrating a point or concept

    oai_token-act-pair · gpt-3.5-turbo

    instances of exemplary situations or phenomena

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urses
    -0.84
    ole
    -0.80
     livest
    -0.78
    reditary
    -0.77
    ief
    -0.76
    ensibly
    -0.76
    ternity
    -0.75
    ormal
    -0.75
    aleigh
    -0.73
    rice
    -0.72
    POSITIVE LOGITS
    wcsstore
    0.88
     illustrating
    0.86
    DragonMagazine
    0.85
    baugh
    0.74
     examples
    0.73
     thereof
    0.73
     demonstrating
    0.71
    é¾įå¥ij士
    0.70
     attRot
    0.69
     illustrates
    0.68
    Act Density 0.031%

    No Known Activations