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

    Neuronpedia

    INDEX
    Explanations

    future predictions or possibilities

    oai_token-act-pair · gpt-3.5-turbo

    expressions of possibility or likelihood regarding future events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    buster
    -0.76
    gypt
    -0.70
     Psychiatry
    -0.68
    alloc
    -0.67
    arily
    -0.65
    hab
    -0.60
    quote
    -0.59
    ogy
    -0.58
    agos
    -0.58
    pose
    -0.58
    POSITIVE LOGITS
     plenty
    1.01
     lots
    0.86
     exceptions
    0.77
     differences
    0.72
     rumors
    0.71
     occasions
    0.70
     some
    0.70
     indications
    0.70
     ample
    0.69
     glimps
    0.69
    Act Density 0.101%

    No Known Activations