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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a conclusion or outcome

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bedo
    -0.14
     Rah
    -0.14
     ÏĢαÏģά
    -0.14
    illon
    -0.14
    unnel
    -0.14
     pressured
    -0.13
    Ïģιο
    -0.13
    nal
    -0.13
     Panic
    -0.13
     pand
    -0.13
    POSITIVE LOGITS
    edException
    0.17
    éī
    0.14
    ellan
    0.14
    aina
    0.14
    uno
    0.14
    ±Ð¾ÑĤ
    0.13
    675
    0.13
    eh
    0.13
    WithContext
    0.13
    olle
    0.13
    Act Density 0.009%

    No Known Activations