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

    Neuronpedia

    INDEX
    Explanations

    words related to scientific terminology and technical discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    r
    -0.23
    rd
    -0.20
    rist
    -0.20
    rug
    -0.19
    ry
    -0.19
    rt
    -0.18
    h
    -0.18
    rint
    -0.18
    rnd
    -0.18
    rh
    -0.17
    POSITIVE LOGITS
    ech
    0.24
    acular
    0.19
    entimes
    0.18
    ekil
    0.17
    itude
    0.17
    ools
    0.17
    ics
    0.17
    ãĤ¥
    0.16
    elligence
    0.16
    egrity
    0.16
    Act Density 0.066%

    No Known Activations