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

    Neuronpedia

    INDEX
    Explanations

    actions that indicate movement or advancement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    @student
    -0.15
    ypass
    -0.15
    ociety
    -0.15
     apparent
    -0.14
    amba
    -0.14
    à¹Ģวà¸Ńร
    -0.14
     pack
    -0.14
     up
    -0.14
    ver
    -0.14
     Sanford
    -0.13
    POSITIVE LOGITS
    ceipt
    0.16
    lesc
    0.15
    uml
    0.15
     stil
    0.15
    /portfolio
    0.15
    å®ŀæĸ½
    0.14
    orgot
    0.14
    undry
    0.14
    aland
    0.14
    esel
    0.14
    Act Density 0.059%

    No Known Activations