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

    Neuronpedia

    INDEX
    Explanations

    capital letters, particularly those at the beginning of sentences or proper nouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ara
    -0.16
    aco
    -0.16
    seealso
    -0.15
    antee
    -0.15
    algo
    -0.15
    usra
    -0.15
    uele
    -0.15
     TAG
    -0.14
    ales
    -0.14
     TZ
    -0.14
    POSITIVE LOGITS
    zf
    0.17
    jah
    0.16
    ecedor
    0.16
    -navbar
    0.16
    zing
    0.16
    osi
    0.15
    etre
    0.15
    zed
    0.15
    zi
    0.15
    ews
    0.15
    Act Density 0.043%

    No Known Activations