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

    Neuronpedia

    INDEX
    Explanations

    extreme negative or painful descriptors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oba
    -0.17
    ogle
    -0.15
    loy
    -0.15
     Ñĥг
    -0.14
    appa
    -0.14
    abile
    -0.14
    CISION
    -0.14
    άβ
    -0.13
    mates
    -0.13
    é¢
    -0.13
    POSITIVE LOGITS
    cular
    0.14
     Burb
    0.14
     Dra
    0.14
     Sommer
    0.14
     surface
    0.14
    andler
    0.14
     circulating
    0.14
    èģĶç½ij
    0.14
     Clara
    0.13
    eca
    0.13
    Act Density 0.008%

    No Known Activations