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

    Neuronpedia

    INDEX
    Explanations

    emotional and physical reactions in characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     amused
    -0.52
     smir
    -0.44
    noopener
    -0.42
     😎
    -0.41
     wink
    -0.40
     disappro
    -0.40
     محفوظة
    -0.39
     läs
    -0.39
     condes
    -0.39
    errHandler
    -0.38
    POSITIVE LOGITS
     shaky
    0.68
     trembling
    0.68
     desperately
    0.67
     stammer
    0.65
     frantically
    0.65
     clutched
    0.61
     fidget
    0.60
     nervously
    0.60
     trembled
    0.56
     clutching
    0.56
    Act Density 0.207%

    No Known Activations