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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating location or position

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     more
    -0.72
    atel
    -0.60
     less
    -0.57
     overall
    -0.55
     similar
    -0.55
     no
    -0.55
     List
    -0.54
    ula
    -0.53
     only
    -0.53
     denn
    -0.53
    POSITIVE LOGITS
    دانشنامهٔ
    0.82
    didSet
    0.81
    :✨
    0.75
     Roskov
    0.74
    Diweddarwch
    0.74
    Portail
    0.74
    ViewFeatures
    0.73
     pulumi
    0.71
    Extinguishing
    0.71
     مُعرِّف
    0.69
    Act Density 0.156%

    No Known Activations