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

    Neuronpedia

    INDEX
    Explanations

    words expressing potential or possibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    помним
    -0.76
    unas
    -0.69
     réguli
    -0.65
    interopRequire
    -0.61
     kanssa
    -0.61
     BoxDecoration
    -0.61
     Pew
    -0.61
    IndentedString
    -0.60
     AAS
    -0.60
    reuung
    -0.58
    POSITIVE LOGITS
     could
    2.59
    could
    2.44
     Could
    2.39
    Could
    2.30
     COULD
    2.30
     podría
    1.69
     pourrait
    1.65
     poderia
    1.64
     könnte
    1.60
     podrían
    1.59
    Act Density 0.079%

    No Known Activations