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

    Neuronpedia

    INDEX
    Explanations

    instances of reasoning or justification that convey logic or coherence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TEL
    -0.16
    ensis
    -0.15
    ensa
    -0.15
    955
    -0.15
    anmar
    -0.14
    aukee
    -0.14
    enschaft
    -0.14
    ielding
    -0.14
    aptors
    -0.14
    imson
    -0.14
    POSITIVE LOGITS
    .updateDynamic
    0.17
     Hüs
    0.16
    empor
    0.15
    morgan
    0.15
    olib
    0.15
    -qu
    0.14
    ken
    0.14
     iconName
    0.14
    vÃŃc
    0.14
    ryption
    0.14
    Act Density 0.016%

    No Known Activations