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

    Neuronpedia

    INDEX
    Explanations

    subtle emotional cues and interactions between characters in a narrative

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and sentence-ending symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ividual
    -0.88
    jri
    -0.84
    regate
    -0.83
     undermin
    -0.79
    isphere
    -0.77
     bilingual
    -0.77
     affili
    -0.76
     commer
    -0.76
     divest
    -0.76
    interstitial
    -0.74
    POSITIVE LOGITS
     Slowly
    1.42
     Suddenly
    1.34
     She
    1.31
     Pyrrha
    1.26
     Somehow
    1.26
     Jaune
    1.24
     Damn
    1.23
     Luckily
    1.21
     Thankfully
    1.21
     His
    1.20
    Act Density 0.181%

    No Known Activations