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

    Neuronpedia

    INDEX
    Explanations

    instances of comparison and critique regarding relationships and societal expectations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iba
    -0.18
     palette
    -0.15
    spi
    -0.15
    kazy
    -0.15
    ibe
    -0.15
    330
    -0.15
    à¹īà¸ĩ
    -0.14
    å®ľ
    -0.14
     drift
    -0.13
    gua
    -0.13
    POSITIVE LOGITS
    cks
    0.19
    _OVERFLOW
    0.17
    utenberg
    0.16
    uren
    0.15
    UGE
    0.14
    UPS
    0.14
    ITTER
    0.14
    ROUP
    0.14
    igar
    0.13
    elu
    0.13
    Act Density 0.081%

    No Known Activations