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

    Neuronpedia

    INDEX
    Explanations

    phrases related to expert recommendations or evaluations

    oai_token-act-pair · gpt-3.5-turbo

    phrases and terms related to recommendations and evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ctor
    -0.72
    ogg
    -0.69
    ãĤ¤ãĥĪ
    -0.68
    cius
    -0.68
     Sabb
    -0.68
    ãĥĩãĤ£
    -0.68
    KK
    -0.67
    Ub
    -0.66
    cler
    -0.66
    ocy
    -0.66
    POSITIVE LOGITS
     for
    0.96
     FOR
    0.84
    for
    0.79
     overboard
    0.71
     agre
    0.70
     lawy
    0.70
    FOR
    0.70
    abase
    0.70
    ioned
    0.67
    anwhile
    0.66
    Act Density 0.169%

    No Known Activations