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

    Neuronpedia

    INDEX
    Explanations

    instances of numerical values and their formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     res
    -0.15
    corn
    -0.15
    U
    -0.14
     ve
    -0.14
    agen
    -0.14
     bout
    -0.14
    holm
    -0.14
    pedia
    -0.14
    LOSS
    -0.14
    udes
    -0.14
    POSITIVE LOGITS
    rais
    0.16
    isson
    0.15
    elmet
    0.14
    élé
    0.14
    лав
    0.14
    ellite
    0.14
    itlement
    0.14
    dle
    0.14
     dane
    0.13
    lac
    0.13
    Act Density 0.003%

    No Known Activations