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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate dissatisfaction or poor performance with products or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eker
    -0.18
    vd
    -0.17
     Mour
    -0.15
     wor
    -0.15
    ght
    -0.15
    ats
    -0.15
    cd
    -0.14
    çĤ
    -0.14
    goo
    -0.14
    ation
    -0.13
    POSITIVE LOGITS
     ÑĢиз
    0.16
    gaard
    0.16
    iná
    0.15
    uada
    0.15
    .square
    0.15
    burgh
    0.14
    _attempt
    0.14
    ุà¸Ĺ
    0.14
    utow
    0.14
     Cube
    0.14
    Act Density 0.264%

    No Known Activations