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

    Neuronpedia

    INDEX
    Explanations

    references to humanitarian issues and the struggles of marginalized populations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .dw
    -0.16
    argon
    -0.15
    bero
    -0.15
    erno
    -0.15
    sterol
    -0.15
    ÙĪÙĬÙĥ
    -0.15
    ompiler
    -0.14
     ngắn
    -0.14
    åIJĽ
    -0.14
    .hxx
    -0.14
    POSITIVE LOGITS
     lives
    0.15
     whose
    0.14
    /~
    0.14
    doch
    0.14
     sat
    0.14
     Lives
    0.14
    ActionTypes
    0.14
    ÑĢовиÑĩ
    0.14
    _operand
    0.13
     world
    0.13
    Act Density 0.249%

    No Known Activations