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

    Neuronpedia

    INDEX
    Explanations

    elements related to relationships and interactions in social contexts

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

    Following conjunctions "and", "or", or a comma

    np_acts-logits-general · gemini-2.0-flash

    lists of actions or things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vœux
    -0.89
    InjectAttribute
    -0.89
     quæ
    -0.87
     chofe
    -0.86
     enfans
    -0.79
     ainfi
    -0.73
     purpoſe
    -0.71
     auffi
    -0.70
     chré
    -0.69
     jsPsych
    -0.68
    POSITIVE LOGITS
     endless
    0.81
     everything
    0.77
     sleepless
    0.74
     lots
    0.70
     conversations
    0.68
     laughter
    0.67
     love
    0.64
     whatnot
    0.64
     music
    0.63
     yes
    0.62
    Act Density 0.280%

    No Known Activations