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

    Neuronpedia

    INDEX
    Explanations

    phrases with the suffix "-ide" that are related to ideologies or classifications

    oai_token-act-pair · gpt-3.5-turbo

    words related to ideology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enegger
    -0.89
    iona
    -0.81
    ions
    -0.79
    é¾
    -0.73
    thening
    -0.72
    wagen
    -0.71
    ufact
    -0.71
    ured
    -0.67
    lished
    -0.67
    ioned
    -0.67
    POSITIVE LOGITS
    gger
    0.96
    maid
    0.87
    creen
    0.84
    ll
    0.80
    ktop
    0.79
    ously
    0.79
    llo
    0.76
    lli
    0.75
    hare
    0.73
    llan
    0.73
    Act Density 0.064%

    No Known Activations