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

    Neuronpedia

    INDEX
    Explanations

    subjective expressions of personal opinions or feelings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aisy
    -0.15
     kuru
    -0.14
    ublic
    -0.14
    arkin
    -0.14
     unt
    -0.14
    kee
    -0.13
    âu
    -0.13
     Stay
    -0.13
    oc
    -0.13
     coc
    -0.13
    POSITIVE LOGITS
    elage
    0.17
    PFN
    0.16
    iaux
    0.15
    caff
    0.15
    robe
    0.15
    landa
    0.15
    toa
    0.15
    æĭ³
    0.15
    تدÙī
    0.14
    sel
    0.14
    Act Density 0.607%

    No Known Activations