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

    Neuronpedia

    INDEX
    Explanations

    references to certainty and decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     manageable
    -0.15
     speeds
    -0.15
    side
    -0.14
     Emanuel
    -0.14
     silent
    -0.14
    odesk
    -0.14
     Speed
    -0.14
    _VISIBLE
    -0.14
    retch
    -0.14
    urgeon
    -0.14
    POSITIVE LOGITS
     Circ
    0.24
    循
    0.21
     circle
    0.20
     circular
    0.20
     Circular
    0.20
     à¤ļà¤ķ
    0.20
     circulation
    0.20
     possibility
    0.20
    circ
    0.19
    -circle
    0.19
    Act Density 0.016%

    No Known Activations