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

    Neuronpedia

    INDEX
    Explanations

    programming constructs and variable manipulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IGGER
    -0.15
    selectAll
    -0.15
    .AutoScaleMode
    -0.14
    borough
    -0.14
    BOVE
    -0.13
    tuk
    -0.13
    upe
    -0.13
    regnum
    -0.13
    mal
    -0.13
    oltip
    -0.13
    POSITIVE LOGITS
    ruz
    0.18
    609
    0.17
    ornings
    0.16
    ario
    0.16
    GraphNode
    0.15
    Ĥ¹
    0.14
    315
    0.14
     Kral
    0.14
    ìĿij
    0.13
    inator
    0.13
    Act Density 0.330%

    No Known Activations