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

    Neuronpedia

    INDEX
    Explanations

    references to dimensionality and spatial concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Constr
    -0.15
    most
    -0.15
    ummy
    -0.14
     tuy
    -0.14
    sov
    -0.14
    lest
    -0.14
    rollo
    -0.14
    svp
    -0.14
    -popup
    -0.13
    rette
    -0.13
    POSITIVE LOGITS
    legg
    0.16
    opath
    0.15
    ogg
    0.15
    agers
    0.15
    ovic
    0.14
     pu
    0.14
    omers
    0.14
    agg
    0.14
    ãĥ¼ãĥ³
    0.14
     ga
    0.14
    Act Density 0.034%

    No Known Activations