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

    Neuronpedia

    INDEX
    Explanations

    references to academic citations or proof structures in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IFF
    -0.15
    amera
    -0.15
     Hubb
    -0.14
    .Generation
    -0.14
    >NN
    -0.14
    erno
    -0.14
    ört
    -0.14
    alley
    -0.14
    orts
    -0.14
    kich
    -0.14
    POSITIVE LOGITS
    irsch
    0.17
    ï¸ı
    0.15
     dec
    0.15
    407
    0.14
     Reich
    0.14
    777
    0.14
    igo
    0.14
    q
    0.14
    essler
    0.14
    ³
    0.13
    Act Density 0.024%

    No Known Activations