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

    Neuronpedia

    INDEX
    Explanations

    affirmatives and agreements in conversational contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     quæ
    -0.69
     يتيمه
    -0.64
    hical
    -0.63
     abstrait
    -0.62
     biologique
    -0.60
     Résultat
    -0.59
    Jeografia
    -0.59
    igraphic
    -0.58
    saraba
    -0.58
    ).__
    -0.58
    POSITIVE LOGITS
     yes
    0.64
    yes
    0.57
     Yes
    0.55
    Yes
    0.55
    @[
    0.52
     Administrativna
    0.50
    ChildIndex
    0.50
    YES
    0.48
     YES
    0.48
    DebuggerStep
    0.47
    Act Density 0.317%

    No Known Activations