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

    Neuronpedia

    INDEX
    Explanations

    references to co-authorship in academic citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unker
    -0.15
    xce
    -0.15
    lett
    -0.14
    odef
    -0.14
    GRAPH
    -0.14
    Pink
    -0.14
    enz
    -0.13
    Pad
    -0.13
    ippo
    -0.13
    xa
    -0.13
    POSITIVE LOGITS
    wich
    0.16
    'gc
    0.15
    izon
    0.14
    hic
    0.14
    hc
    0.14
    erken
    0.14
    marsh
    0.14
    одаÑĢ
    0.14
    ाण
    0.14
    \Context
    0.13
    Act Density 0.011%

    No Known Activations