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

    Neuronpedia

    INDEX
    Explanations

    references to specific academic articles and their citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ama
    -0.22
    ortal
    -0.20
    undra
    -0.20
    undo
    -0.18
    á»Ļt
    -0.18
    yst
    -0.17
    agne
    -0.16
    MP
    -0.15
    ensen
    -0.15
    inecraft
    -0.15
    POSITIVE LOGITS
    imos
    0.17
    ox
    0.17
     Whit
    0.16
    aber
    0.16
    anton
    0.16
    rio
    0.15
    ow
    0.15
    itor
    0.15
    oe
    0.15
    aw
    0.15
    Act Density 0.167%

    No Known Activations