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

    Neuronpedia

    INDEX
    Explanations

    references to social issues related to diversity and inclusivity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     LoggerFactory
    -0.71
     Wicidata
    -0.69
     uVar
    -0.69
    UnknownFields
    -0.66
    Pfalz
    -0.64
     bezeichneter
    -0.64
    ();)
    -0.63
     surla
    -0.62
    DECREF
    -0.62
    FieldBuilder
    -0.61
    POSITIVE LOGITS
     gender
    0.89
     feminist
    0.75
     Gender
    0.75
    gender
    0.74
     LGBTQ
    0.72
    LGBT
    0.68
    Gender
    0.66
     Feminist
    0.65
     racial
    0.64
     equality
    0.64
    Act Density 0.347%

    No Known Activations