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

    Neuronpedia

    INDEX
    Explanations

    conversational interactions between characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows a character's name, then an action

    np_acts-logits-general · gemini-2.0-flash

    expressions of reaction and posture

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -0.58
     Référence
    -0.57
    ImageContext
    -0.56
     continúas
    -0.55
     AssemblyVersion
    -0.50
    ReusableCell
    -0.50
    allee
    -0.49
     snippetHide
    -0.48
     assoluto
    -0.47
     nemico
    -0.47
    POSITIVE LOGITS
     chuckle
    0.97
     chuckled
    0.96
     chuckles
    0.94
     snorted
    0.92
     roll
    0.92
     rolls
    0.91
     rolled
    0.90
     shrug
    0.88
     shrugged
    0.87
     shrugs
    0.85
    Act Density 0.143%

    No Known Activations