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

    Neuronpedia

    INDEX
    Explanations

    negative values or expressions related to negativity

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ukone
    -0.61
    شهاد
    -0.59
    hdashline
    -0.58
    aspectj
    -0.56
    +:+
    -0.56
     RouterModule
    -0.55
    AndEndTag
    -0.54
    abatic
    -0.52
    phazard
    -0.51
    atguigu
    -0.50
    POSITIVE LOGITS
     lenker
    0.67
     بيها
    0.62
     pedimos
    0.60
    ℉
    0.60
    IsContent
    0.58
     clientele
    0.57
     mack
    0.56
    irage
    0.55
    Mack
    0.55
     Untersch
    0.55
    Act Density 0.006%

    No Known Activations