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

    Neuronpedia

    INDEX
    Explanations

    sentences related to legal actions or criminal activities

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks or sentence terminators, indicating the conclusion of statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     instinct
    -0.75
     pudding
    -0.74
     calming
    -0.73
     powering
    -0.70
     impuls
    -0.70
     facult
    -0.69
     empowerment
    -0.69
     perspect
    -0.69
     meddling
    -0.68
     lips
    -0.67
    POSITIVE LOGITS
     Each
    1.68
     Among
    1.68
     These
    1.66
     Those
    1.59
     Others
    1.51
     None
    1.50
     Included
    1.46
    Among
    1.43
     Some
    1.43
     Including
    1.40
    Act Density 0.543%

    No Known Activations