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

    Neuronpedia

    INDEX
    Explanations

    mentions of prominent media sources and publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    098
    -0.16
    097
    -0.16
    vek
    -0.15
    aic
    -0.14
    087
    -0.14
    781
    -0.13
     overhead
    -0.13
    ı
    -0.13
    ignon
    -0.13
    549
    -0.13
    POSITIVE LOGITS
     why
    0.18
     exclusively
    0.17
    why
    0.17
    ousel
    0.16
    ãĥĭãĥ¼
    0.15
    /Dk
    0.15
    ÃĹ↵↵
    0.15
     earlier
    0.14
     via
    0.14
     ';↵↵
    0.14
    Act Density 0.026%

    No Known Activations