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

    Neuronpedia

    INDEX
    Explanations

    phrases related to cosmetic or superficial attributes and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Kramer
    -0.15
     clearing
    -0.15
    plusplus
    -0.15
     des
    -0.14
    ollo
    -0.14
     marches
    -0.14
    ulla
    -0.14
    oldem
    -0.14
    elves
    -0.14
    occo
    -0.14
    POSITIVE LOGITS
    ylon
    0.17
    ìĤ¬íķŃ
    0.16
     ìĤ¬íķŃ
    0.15
    inkle
    0.15
    decorate
    0.14
    oma
    0.14
    affer
    0.14
    rud
    0.13
    krom
    0.13
    MLE
    0.13
    Act Density 0.002%

    No Known Activations