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

    Neuronpedia

    INDEX
    Explanations

    instances of specific numeric values or coded representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     '[
    -0.16
    '[
    -0.15
    )[
    -0.15
    ).[
    -0.14
     Guth
    -0.14
    ROTO
    -0.14
    otec
    -0.14
    LOB
    -0.14
     Russ
    -0.14
    vid
    -0.14
    POSITIVE LOGITS
     Moon
    0.24
     voice
    0.24
     Voice
    0.21
     jack
    0.21
    -↵
    0.21
    -↵↵
    0.21
    Moon
    0.21
    -*
    0.20
     voices
    0.19
    –↵↵
    0.19
    Act Density 0.000%

    No Known Activations