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

    Neuronpedia

    INDEX
    Explanations

    references to rules, guidelines, or structured methodologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tok
    -0.15
    anke
    -0.14
    cir
    -0.14
    cash
    -0.14
    eddar
    -0.13
    hawk
    -0.13
    burgh
    -0.13
    ira
    -0.13
    plied
    -0.13
    ichel
    -0.13
    POSITIVE LOGITS
    ayd
    0.17
    ÑģÑĮ
    0.16
    vailable
    0.15
    eah
    0.15
    ufe
    0.14
     tay
    0.14
    /as
    0.14
    mlink
    0.14
    portlet
    0.14
     principles
    0.13
    Act Density 0.058%

    No Known Activations