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

    Neuronpedia

    INDEX
    Explanations

    words related to homosexuality and its discussions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Diri
    -0.81
    Skocz
    -0.80
     carina
    -0.79
     Taka
    -0.77
     Johnnie
    -0.76
     Infórmanos
    -0.73
     Dort
    -0.72
    cair
    -0.71
    Taka
    -0.71
    ítulo
    -0.70
    POSITIVE LOGITS
     Hom
    1.44
     hom
    1.38
    Hom
    1.34
    hom
    1.25
     homogen
    1.02
     HOM
    0.96
    HOM
    0.96
     homosexual
    0.88
     homog
    0.81
     homophobic
    0.81
    Act Density 0.012%

    No Known Activations