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

    Neuronpedia

    INDEX
    Explanations

    references to quantities or vague numerical descriptors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    347
    -0.16
    ritten
    -0.15
     Gim
    -0.14
    rompt
    -0.14
    ola
    -0.14
    iki
    -0.14
    vyÅ¡Å¡ÃŃ
    -0.14
    424
    -0.14
    opause
    -0.13
    ilia
    -0.13
    POSITIVE LOGITS
    unately
    0.22
     instance
    0.20
     sake
    0.20
     example
    0.19
     reasons
    0.17
    enco
    0.17
     purposes
    0.17
    ced
    0.17
    ged
    0.16
    InstanceState
    0.16
    Act Density 0.073%

    No Known Activations