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

    Neuronpedia

    INDEX
    Explanations

    negative descriptors related to dishonesty or low quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eless
    -0.16
     unfavor
    -0.15
    lek
    -0.15
    anford
    -0.15
    isay
    -0.15
    dr
    -0.14
     oppon
    -0.14
     occasion
    -0.14
    iki
    -0.14
    riv
    -0.13
    POSITIVE LOGITS
    ÛĮز
    0.17
    anske
    0.16
    aires
    0.16
     Winds
    0.15
    .ide
    0.15
    agan
    0.15
    VILLE
    0.15
    pus
    0.15
    ville
    0.14
     Coh
    0.14
    Act Density 0.073%

    No Known Activations