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

    Neuronpedia

    INDEX
    Explanations

    references to specific concepts or subjects within discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isiyle
    -0.16
    ãĥĪãĥ«
    -0.15
    erview
    -0.15
    addin
    -0.15
    âh
    -0.14
    bert
    -0.14
    SMART
    -0.14
    ÑĢедиÑĤ
    -0.14
    å´İ
    -0.14
     rent
    -0.14
    POSITIVE LOGITS
    qw
    0.16
    ungan
    0.15
    lw
    0.15
    adir
    0.15
    opp
    0.14
    anie
    0.14
    ìĦł
    0.14
    ipa
    0.14
    ocal
    0.14
     Dw
    0.14
    Act Density 0.080%

    No Known Activations