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

    Neuronpedia

    INDEX
    Explanations

    conversational elements and emotional expressions in dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Alte
    -0.41
     الرياضيه
    -0.40
     بیر
    -0.35
     <>",
    -0.34
    ulos
    -0.33
     securing
    -0.32
     transfieras
    -0.32
     EdgeInsets
    -0.32
    bait
    -0.32
    Alte
    -0.31
    POSITIVE LOGITS
     silence
    0.66
     silêncio
    0.63
    parsedMessage
    0.61
     speechless
    0.60
     silent
    0.60
     Silence
    0.59
    silence
    0.59
     صوتيه
    0.59
     témoig
    0.58
     silenced
    0.57
    Act Density 0.253%

    No Known Activations