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

    Neuronpedia

    INDEX
    Explanations

    words related to technical elements such as programming or configuration

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "oe" across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ifiable
    -0.86
    ifiers
    -0.86
    rons
    -0.81
    ifier
    -0.77
     glim
    -0.76
    ifications
    -0.71
    arians
    -0.69
    abad
    -0.66
    iques
    -0.66
    naires
    -0.65
    POSITIVE LOGITS
    ppel
    1.20
    hner
    1.11
    hler
    1.09
    zie
    1.06
    cean
    1.05
    zzi
    1.05
    lect
    1.04
    cker
    1.02
    utenant
    0.98
    ffer
    0.97
    Act Density 0.041%

    No Known Activations