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

    Neuronpedia

    INDEX
    Explanations

    adverbs indicating certainty or strong emphasis

    oai_token-act-pair · gpt-3.5-turbo

    assertive language indicating certainty or definitiveness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     respectively
    -0.77
    entary
    -0.76
    ingly
    -0.75
    awaru
    -0.71
    atem
    -0.70
    oru
    -0.70
    roups
    -0.68
    glers
    -0.67
    ultimate
    -0.66
    ENCY
    -0.65
    POSITIVE LOGITS
     qualifies
    0.80
     deserved
    0.73
     wasn
    0.73
     not
    0.73
     NOT
    0.69
     wouldn
    0.69
     deserve
    0.69
     wont
    0.68
     deserves
    0.68
     weren
    0.68
    Act Density 0.082%

    No Known Activations