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

    Neuronpedia

    INDEX
    Explanations

    short sentences or quotes with specific punctuation patterns

    oai_token-act-pair · gpt-3.5-turbo

    phrases or expressions of surprise or disbelief

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     destro
    -0.68
     overdoses
    -0.65
     runaway
    -0.65
     marquee
    -0.65
     plummet
    -0.64
     mammoth
    -0.64
    interstitial
    -0.64
     sustaining
    -0.63
     culminating
    -0.63
     overdose
    -0.63
    POSITIVE LOGITS
    Question
    0.99
    Correct
    0.98
    âĶĢâĶĢâĶĢâĶĢ
    0.96
    Yeah
    0.94
    laughs
    0.87
    laugh
    0.87
    Answer
    0.86
    Interview
    0.86
    Actually
    0.85
    Regarding
    0.84
    Act Density 0.535%

    No Known Activations