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

    Neuronpedia

    INDEX
    Explanations

    discussions around gender roles and inequalities

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    enterOuterAlt
    -0.67
    setVerticalGroup
    -0.49
    addPreferredGap
    -0.49
    omethane
    -0.47
     Dun
    -0.46
    pushFollow
    -0.46
    IEnumerator
    -0.45
    GIVEREF
    -0.45
    Населення
    -0.44
    zieży
    -0.43
    POSITIVE LOGITS
     fémin
    1.09
     female
    1.07
     feminina
    1.07
     Female
    1.05
     féminine
    1.05
    female
    1.04
    Female
    1.04
     féminin
    1.04
     feminine
    1.03
     Females
    1.02
    Act Density 0.283%

    No Known Activations