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

    Neuronpedia

    INDEX
    Explanations

    references to similarity or comparison between items or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dymyr
    -0.67
    kette
    -0.63
    es
    -0.63
     voz
    -0.58
     ste
    -0.56
    زه
    -0.54
     *
    -0.53
     voice
    -0.53
    넘
    -0.52
     sto
    -0.52
    POSITIVE LOGITS
     similar
    1.67
    similar
    1.65
    Similar
    1.64
     Similar
    1.64
     SIMILAR
    1.62
     similaire
    1.35
     simil
    1.30
    RectangleBorder
    1.27
    Похо
    1.25
    iliar
    1.22
    Act Density 0.111%

    No Known Activations