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

    Neuronpedia

    INDEX
    Explanations

    references to specific objects, actions, and characteristics within a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ey
    -0.28
    y
    -0.24
    en
    -0.24
    ek
    -0.24
    ens
    -0.23
    ela
    -0.23
    ery
    -0.23
    erville
    -0.21
    ert
    -0.21
    els
    -0.20
    POSITIVE LOGITS
    er
    0.30
    hyth
    0.28
    hythm
    0.28
    erer
    0.27
    idge
    0.26
    iginal
    0.25
    ød
    0.23
    land
    0.23
    ë§ģ
    0.22
    anged
    0.22
    Act Density 2.735%

    No Known Activations