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

    Neuronpedia

    INDEX
    Explanations

    references to biases and equality issues within social contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    configs
    -0.14
    ÏĥοÏħ
    -0.13
    047
    -0.12
    ÏĢλ
    -0.12
    thew
    -0.12
    helpers
    -0.12
    053
    -0.12
     feather
    -0.12
    pagen
    -0.12
    DMIN
    -0.12
    POSITIVE LOGITS
    MESS
    0.15
    culo
    0.15
     Byl
    0.14
    otto
    0.14
    jed
    0.13
    rello
    0.13
    ellow
    0.12
    raquo
    0.12
     Barry
    0.12
    iá»ĥm
    0.12
    Act Density 0.560%

    No Known Activations