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

    Neuronpedia

    INDEX
    Explanations

    mentions of the word "nose"

    oai_token-act-pair · gpt-3.5-turbo

    words related to conditions or attributes associated with excess

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ersen
    -0.79
    icum
    -0.72
    angible
    -0.71
    ufact
    -0.71
    azon
    -0.71
    agna
    -0.69
    rators
    -0.69
    oola
    -0.69
    cdn
    -0.67
    enberg
    -0.66
    POSITIVE LOGITS
    velt
    1.05
    cond
    1.03
    idon
    1.01
    lihood
    1.00
    lect
    0.94
    LECT
    0.85
    eker
    0.82
    ï¸
    0.79
    OPLE
    0.78
    ols
    0.77
    Act Density 0.022%

    No Known Activations