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

    Neuronpedia

    INDEX
    Explanations

    references to scientific research and findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ics
    -0.19
    uma
    -0.16
    undry
    -0.15
    anders
    -0.15
    ocol
    -0.15
    isman
    -0.15
    kas
    -0.15
    Ñıв
    -0.14
    prof
    -0.14
    loid
    -0.14
    POSITIVE LOGITS
    ally
    0.39
    ALLY
    0.30
    ity
    0.20
    /engine
    0.19
     breakthrough
    0.17
    xffffffff
    0.16
    -community
    0.16
    -cultural
    0.16
    -commercial
    0.15
    /math
    0.15
    Act Density 0.011%

    No Known Activations