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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating agreements, contracts, or formal commitments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    harma
    -0.15
    pec
    -0.15
    adors
    -0.15
     Lauderdale
    -0.15
    Configurer
    -0.15
    rored
    -0.14
    ãĥ¼ãĥ³
    -0.14
    ecs
    -0.14
    osas
    -0.14
    _SCALE
    -0.14
    POSITIVE LOGITS
    ÑĥзÑĭ
    0.16
    idi
    0.15
    auty
    0.14
    094
    0.14
    isz
    0.14
    cep
    0.14
    arde
    0.14
    lique
    0.14
    owell
    0.14
    apur
    0.14
    Act Density 0.000%

    No Known Activations