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

    Neuronpedia

    INDEX
    Explanations

    adjectives that describe characteristics or qualities

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Delia
    -0.86
     Paglinawan
    -0.86
    fecture
    -0.84
     crows
    -0.83
     virgins
    -0.83
     virginity
    -0.81
     imputation
    -0.81
    manteau
    -0.79
    ausea
    -0.79
    Slf
    -0.79
    POSITIVE LOGITS
    idal
    0.67
    cing
    0.59
    led
    0.56
    }')
    0.56
    zyła
    0.56
     pá
    0.56
    ided
    0.56
    cer
    0.52
    ced
    0.52
    InstanceOf
    0.52
    Act Density 0.040%

    No Known Activations