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

    Neuronpedia

    INDEX
    Explanations

    conversational exchanges and dialogues between characters

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

    A character's name followed by an action

    np_acts-logits-general · gemini-2.0-flash

    names followed by actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GEBURTSDATUM
    -0.64
     ambassade
    -0.61
    DialogComponent
    -0.60
    serves
    -0.58
    المشاركات
    -0.58
    olastic
    -0.58
    PMailer
    -0.58
    contentLoaded
    -0.56
    hdessä
    -0.56
     виправивши
    -0.56
    POSITIVE LOGITS
     smiled
    0.95
     chuckled
    0.82
     smirked
    0.81
     grinned
    0.81
     smile
    0.81
     shrugged
    0.78
     nodded
    0.77
     looked
    0.77
     glanced
    0.75
     smir
    0.74
    Act Density 0.136%

    No Known Activations