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

    Neuronpedia

    INDEX
    Explanations

    emotional expressions and shifts in sentiment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     NSCoder
    -0.99
     виправивши
    -0.97
     typelib
    -0.87
     snippetHide
    -0.86
    expandindo
    -0.85
     بيها
    -0.84
    featureID
    -0.83
    ("")]
    -0.80
     متعلقه
    -0.80
    ########.
    -0.79
    POSITIVE LOGITS
    Then
    0.58
    then
    0.53
     Then
    0.52
    Anyway
    0.52
     Anyway
    0.50
     then
    0.50
     Затем
    0.46
    Finally
    0.46
     Finally
    0.45
    but
    0.45
    Act Density 0.111%

    No Known Activations