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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing strong opinions or evaluations, particularly with words like "worst," "best," "certainly," and "good."

    oai_token-act-pair · gpt-3.5-turbo

    negative assessments or criticisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Accountability
    -0.47
     Talks
    -0.46
    CHAT
    -0.46
     Responsibility
    -0.45
     Dialogue
    -0.43
     Jude
    -0.41
     Wikimedia
    -0.41
     Culture
    -0.41
     Faul
    -0.40
     Investigative
    -0.40
    POSITIVE LOGITS
     suffice
    0.55
    uable
    0.53
    iatus
    0.51
    esides
    0.49
    ecided
    0.48
     bother
    0.48
     detract
    0.47
    ean
    0.46
     imaginable
    0.44
     dissu
    0.44
    Act Density 5.730%

    No Known Activations