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

    Neuronpedia

    INDEX
    Explanations

    words related to gender identity and political/social controversy

    oai_token-act-pair · gpt-3.5-turbo

    terms related to gender identity and its implications in society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Sequ
    -0.75
     explan
    -0.68
     obser
    -0.65
     tremend
    -0.64
     newcom
    -0.62
    cknowled
    -0.62
     millenn
    -0.62
     reconc
    -0.61
    Weak
    -0.59
    repre
    -0.59
    POSITIVE LOGITS
     anymore
    0.83
    .
    0.83
    .''.
    0.77
     whatsoever
    0.70
     or
    0.70
    .[
    0.70
    *.
    0.68
    .,"
    0.68
     Getty
    0.67
    ãĢĤ
    0.63
    Act Density 0.580%

    No Known Activations