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

    Neuronpedia

    INDEX
    Explanations

    hexadecimal values and code-related structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    939
    -0.17
    945
    -0.16
    166
    -0.16
    ucer
    -0.15
    299
    -0.14
     fou
    -0.14
    297
    -0.14
    365
    -0.14
    XXX
    -0.14
    366
    -0.14
    POSITIVE LOGITS
    800
    0.19
     DEAD
    0.18
    feed
    0.18
    dead
    0.18
    assis
    0.17
     dead
    0.16
     Dead
    0.16
    %x
    0.15
     FE
    0.15
     FF
    0.15
    Act Density 0.016%

    No Known Activations