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

    Neuronpedia

    INDEX
    Explanations

    binary or hexadecimal values in a code or data structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    939
    -0.18
     hypo
    -0.15
    993
    -0.14
    osu
    -0.14
    igner
    -0.14
    OLDER
    -0.14
    749
    -0.14
    299
    -0.14
    ANGLES
    -0.14
    297
    -0.13
    POSITIVE LOGITS
     DEAD
    0.24
    800
    0.23
    000
    0.23
    dead
    0.21
     Dead
    0.20
     dead
    0.20
     FF
    0.19
    FE
    0.19
     FE
    0.19
    _dead
    0.18
    Act Density 0.015%

    No Known Activations