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

    Neuronpedia

    INDEX
    Explanations

    specific numerical values and identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    undry
    -0.17
     favour
    -0.17
    MER
    -0.16
    è©ŀ
    -0.15
    _PROTO
    -0.14
    Pes
    -0.14
    abbo
    -0.14
    peaker
    -0.14
    rex
    -0.14
    ÑĤÑİ
    -0.14
    POSITIVE LOGITS
     foot
    0.16
     SOUR
    0.14
     inv
    0.14
    аÑĢамеÑĤ
    0.14
    hof
    0.14
    embro
    0.14
    yah
    0.14
    izzo
    0.13
     gam
    0.13
    .actor
    0.13
    Act Density 0.020%

    No Known Activations