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

    Neuronpedia

    INDEX
    Explanations

    negative words or phrases indicating dissatisfaction or frustration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rière
    -0.17
    .scalablytyped
    -0.17
    άνα
    -0.16
    ãĥĥãĥĦ
    -0.16
    uum
    -0.15
    ozor
    -0.15
    chandle
    -0.15
     ì·¨
    -0.14
    indo
    -0.14
    qx
    -0.14
    POSITIVE LOGITS
    епÑĤи
    0.18
    ÑĨÑĸ
    0.15
    cent
    0.14
    ubits
    0.14
    andler
    0.14
    ÏĢη
    0.14
    FACE
    0.13
     popularity
    0.13
    ادت
    0.13
    еп
    0.13
    Act Density 0.207%

    No Known Activations