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

    Neuronpedia

    INDEX
    Explanations

    references to natural elements and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    estion
    -0.18
    idel
    -0.18
    LabelText
    -0.16
    ën
    -0.14
    ÙĨاÙħÙĩ
    -0.14
    nh
    -0.14
    nev
    -0.14
    eb
    -0.14
    Ñģол
    -0.14
    ossible
    -0.14
    POSITIVE LOGITS
    istic
    0.29
    istically
    0.26
    mente
    0.21
    fully
    0.19
    /native
    0.19
    ized
    0.18
    ERSHEY
    0.18
    arkan
    0.15
    iste
    0.15
    ised
    0.15
    Act Density 0.048%

    No Known Activations