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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "individuals" and its variations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Roskov
    -0.83
     juzg
    -0.72
     betweenstory
    -0.68
     Sando
    -0.66
     shampo
    -0.66
     shopkeeper
    -0.65
     glucocortico
    -0.64
     Taran
    -0.63
    Personensuche
    -0.63
     watchman
    -0.63
    POSITIVE LOGITS
    Parabéns
    0.73
    pportun
    0.71
    digm
    0.71
    fible
    0.69
    çalves
    0.69
    ISTRATION
    0.68
    antity
    0.67
    setHorizontal
    0.66
    roits
    0.66
    GINIA
    0.65
    Act Density 0.010%

    No Known Activations