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

    Neuronpedia

    INDEX
    Explanations

    documentation or instructions related to coding and software processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elves
    -0.16
    ifter
    -0.15
    aims
    -0.15
    ilo
    -0.15
    itori
    -0.14
    safe
    -0.14
     çŃ
    -0.14
    å¸Ń
    -0.14
    hani
    -0.14
    haft
    -0.14
    POSITIVE LOGITS
    vere
    0.16
    erland
    0.15
    lemn
    0.15
    pla
    0.14
    pak
    0.14
     precision
    0.14
    bound
    0.14
    ÑĭÑĤ
    0.13
     cazzo
    0.13
    celik
    0.13
    Act Density 0.021%

    No Known Activations