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

    Neuronpedia

    INDEX
    Explanations

    phrases related to different types of actions or activities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of women and their associated experiences in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iths
    -0.67
    ilies
    -0.67
    stals
    -0.66
    qus
    -0.64
    eele
    -0.64
    aughs
    -0.64
    uties
    -0.63
    hua
    -0.63
     tongues
    -0.63
    rosso
    -0.62
    POSITIVE LOGITS
     imaginable
    1.64
     conceivable
    1.16
     except
    0.99
    except
    0.86
     whatsoever
    0.83
     ounce
    0.79
    nut
    0.76
    soever
    0.76
    winner
    0.75
    oso
    0.72
    Act Density 0.170%

    No Known Activations