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

    Neuronpedia

    INDEX
    Explanations

    humorous or whimsical descriptions of situations and characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ække
    -0.18
    ihan
    -0.18
    actics
    -0.14
    iversit
    -0.14
    ãģ£ãģį
    -0.14
     ãĤ¢ãĥ«
    -0.14
     Paz
    -0.14
    ouz
    -0.14
    ادات
    -0.14
    nable
    -0.14
    POSITIVE LOGITS
    opping
    0.15
    chas
    0.14
    ำ
    0.14
     اÙĦعÙħ
    0.14
     chắc
    0.14
    uffers
    0.14
    illing
    0.14
     ;č↵
    0.14
     Horton
    0.13
    .cls
    0.13
    Act Density 0.500%

    No Known Activations