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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, specifically names and titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ed
    -0.30
    es
    -0.27
    elle
    -0.25
    edback
    -0.23
    ally
    -0.22
    LY
    -0.22
    eded
    -0.21
    et
    -0.21
    el
    -0.21
    ela
    -0.21
    POSITIVE LOGITS
    dehyde
    0.30
    icious
    0.27
    gebra
    0.27
    cohol
    0.26
    phabet
    0.25
    ateral
    0.23
    ypse
    0.23
    gorithms
    0.23
    ogue
    0.22
    umni
    0.21
    Act Density 0.100%

    No Known Activations