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

    Neuronpedia

    INDEX
    Explanations

    references to societal issues and consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    won
    -0.18
    odyn
    -0.16
    alar
    -0.15
    vant
    -0.14
    isan
    -0.14
    ÙĬÙĦØ©
    -0.14
     Dann
    -0.14
    alia
    -0.14
    Å¡it
    -0.14
    kit
    -0.13
    POSITIVE LOGITS
    ayette
    0.16
    enance
    0.14
    ür
    0.14
    ÅĤaw
    0.13
     OTHERWISE
    0.13
    à¸Ĺà¸Ńà¸ĩ
    0.13
    duce
    0.13
     пÑĢиÑħод
    0.13
     Battlefield
    0.13
    è¿IJ
    0.13
    Act Density 0.285%

    No Known Activations