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

    Neuronpedia

    INDEX
    Explanations

    instructions related to website functionality and user interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abor
    -0.17
    aylor
    -0.17
    mart
    -0.15
    ount
    -0.15
    ogle
    -0.14
    ingleton
    -0.14
    ennen
    -0.14
    istrovstvÃŃ
    -0.14
    ħ§
    -0.14
     nowhere
    -0.14
    POSITIVE LOGITS
    AVE
    0.16
    ecessary
    0.16
    ANEL
    0.15
    usal
    0.15
    anagan
    0.14
    áºŃn
    0.14
    cente
    0.14
    æĵ
    0.14
    ulings
    0.13
    =YES
    0.13
    Act Density 0.067%

    No Known Activations