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

    Neuronpedia

    INDEX
    Explanations

    mentions of rankings or numerical orders

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zem
    -0.16
     reap
    -0.14
    ousel
    -0.14
    å§ĭ
    -0.14
    855
    -0.14
    PRINTF
    -0.14
     labor
    -0.14
    enate
    -0.14
    .BLL
    -0.14
    ouri
    -0.13
    POSITIVE LOGITS
    ivot
    0.16
    onde
    0.15
    ETHOD
    0.15
    ENTS
    0.14
    ilon
    0.14
    atters
    0.14
    oriously
    0.14
    igits
    0.14
    aida
    0.14
    _defined
    0.13
    Act Density 0.009%

    No Known Activations