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

    Neuronpedia

    INDEX
    Explanations

    phrases related to criticizing actions or statements

    oai_token-act-pair · gpt-3.5-turbo

    references to accountability or consequences associated with actions or behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wolves
    -0.70
     sources
    -0.68
     alternatives
    -0.67
    FIELD
    -0.64
     fellows
    -0.62
    ods
    -0.61
    andals
    -0.61
    kees
    -0.60
    ergic
    -0.58
     Options
    -0.58
    POSITIVE LOGITS
     every
    1.91
    every
    1.84
    Every
    1.68
     Every
    1.67
     EVERY
    1.55
    each
    1.22
    Each
    1.18
     each
    1.17
     Each
    1.13
     everybody
    1.01
    Act Density 0.275%

    No Known Activations