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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, specifically commas

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "to do that," indicating actions or instructions being discussed

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    assed
    -0.65
    arov
    -0.64
    Detailed
    -0.63
    etheless
    -0.62
    caster
    -0.61
    Uk
    -0.60
    rou
    -0.60
    NBA
    -0.59
    bor
    -0.58
    Bride
    -0.57
    POSITIVE LOGITS
     however
    1.23
     moreover
    0.99
    SPONSORED
    0.88
     though
    0.87
     alas
    0.78
     according
    0.75
     please
    0.72
    isen
    0.70
     we
    0.70
     meanwhile
    0.67
    Act Density 0.247%

    No Known Activations