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

    Neuronpedia

    INDEX
    Explanations

    instances of phrases indicating belief and trust

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    legate
    -0.15
    TERS
    -0.14
    ignment
    -0.14
    legates
    -0.14
    agment
    -0.14
    mium
    -0.14
    enade
    -0.14
    lf
    -0.13
    anes
    -0.13
    afi
    -0.13
    POSITIVE LOGITS
    ?
    0.16
     underst
    0.16
    etheless
    0.15
     though
    0.15
    prisingly
    0.14
    umably
    0.14
    identally
    0.14
    ÙĮ
    0.14
    pecially
    0.14
    theless
    0.14
    Act Density 0.269%

    No Known Activations