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

    Neuronpedia

    INDEX
    Explanations

    dialogues and character interactions within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    دانشنامهٔ
    -0.67
    (")");
    -0.64
    expandindo
    -0.60
    — 
    -0.59
    principalTable
    -0.59
     виправивши
    -0.59
     powied
    -0.58
     transfieras
    -0.58
    saying
    -0.56
     autorytatywna
    -0.56
    POSITIVE LOGITS
     while
    0.84
     terwijl
    0.72
     after
    0.70
     sambil
    0.64
     whilst
    0.64
     tone
    0.62
     sounding
    0.61
     aloud
    0.60
     softly
    0.60
     before
    0.59
    Act Density 0.056%

    No Known Activations