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

    Neuronpedia

    INDEX
    Explanations

    specific nouns related to physical objects and concepts of stability or governance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
                    ↵
    -0.23
     storm
    -0.19
     strokes
    -0.19
     sting
    -0.19
     stationed
    -0.18
    				↵
    -0.18
    ameda
    -0.18
     stated
    -0.18
     statements
    -0.18
    _students
    -0.18
    POSITIVE LOGITS
    coach
    0.19
    bucks
    0.19
    cipher
    0.18
    -alone
    0.18
    vation
    0.18
    craft
    0.17
     lại
    0.16
     quo
    0.16
    inger
    0.16
    islav
    0.16
    Act Density 0.356%

    No Known Activations