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

    Neuronpedia

    INDEX
    Explanations

    adjectives related to characteristics or conditions

    oai_token-act-pair · gpt-3.5-turbo

    words related to injuries and physical conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sidel
    -0.61
     Nept
    -0.60
     Dul
    -0.59
     Das
    -0.56
     Dres
    -0.55
     Torrent
    -0.53
     Allaah
    -0.53
     Muk
    -0.52
     Wim
    -0.52
     Lod
    -0.52
    POSITIVE LOGITS
    y
    3.12
    iness
    1.76
    ily
    1.71
    iest
    1.67
    yk
    1.60
    yg
    1.59
    ies
    1.52
    yi
    1.52
    eenth
    1.49
    yt
    1.48
    Act Density 0.268%

    No Known Activations