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

    Neuronpedia

    INDEX
    Explanations

    colons indicating lists or enumerations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    :
    -0.19
    :↵
    -0.17
    ↵
    -0.17
    (
    -0.17
    s
    -0.16
    d
    -0.16
    ’n
    -0.15
    ahy
    -0.15
    644
    -0.14
    672
    -0.14
    POSITIVE LOGITS
    00
    0.30
    30
    0.23
    05
    0.19
    reau
    0.17
    istrovstvÃŃ
    0.16
    02
    0.16
    òi
    0.15
    _vm
    0.15
    04
    0.15
    45
    0.15
    Act Density 0.113%

    No Known Activations