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

    Neuronpedia

    INDEX
    Explanations

    numerals and page-related references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     acronym
    -0.16
     hun
    -0.15
    ament
    -0.15
     atte
    -0.15
     visc
    -0.15
    ledo
    -0.14
    asar
    -0.14
    ng
    -0.14
     Themes
    -0.14
    uters
    -0.14
    POSITIVE LOGITS
    -BEGIN
    0.19
    ÑĤÑĢо
    0.17
    esub
    0.15
    exion
    0.15
    ož
    0.15
    _pref
    0.15
     McKay
    0.14
     ifndef
    0.14
    _PREF
    0.14
    iguiente
    0.14
    Act Density 0.002%

    No Known Activations