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

    Neuronpedia

    INDEX
    Explanations

    nouns and terms related to scientific processes and astrophysics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hoe
    -0.15
    aginator
    -0.15
     Ted
    -0.14
    open
    -0.14
     Bye
    -0.14
    cape
    -0.13
    Delayed
    -0.13
     Howard
    -0.13
     Directions
    -0.13
    ourt
    -0.13
    POSITIVE LOGITS
    ervas
    0.18
    ewis
    0.17
    eah
    0.16
    ocale
    0.15
     denn
    0.15
    STRU
    0.15
    è³¢
    0.15
    wnd
    0.15
    erville
    0.14
    URITY
    0.14
    Act Density 0.002%

    No Known Activations