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

    Neuronpedia

    INDEX
    Explanations

    the word "maybe" in sentences

    oai_token-act-pair · gpt-3.5-turbo

    suggestions or possibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cies
    -0.92
    ife
    -0.89
    lete
    -0.83
    iak
    -0.82
    ocaust
    -0.80
    ament
    -0.79
    ken
    -0.78
    ombat
    -0.76
    arthed
    -0.76
    nen
    -0.76
    POSITIVE LOGITS
     someday
    1.10
     subconscious
    0.78
     misunder
    0.68
     opio
    0.67
     unsurprisingly
    0.66
    haps
    0.66
     overlook
    0.65
     unemploy
    0.65
     SOME
    0.65
     sensing
    0.65
    Act Density 0.028%

    No Known Activations