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

    Neuronpedia

    INDEX
    Explanations

    terms related to medical or procedural advantages and safety

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     YOU
    -0.61
     specs
    -0.56
     you
    -0.54
    YOU
    -0.53
     fights
    -0.51
     moms
    -0.50
    HUMAN
    -0.50
     your
    -0.50
    …
    -0.50
     loves
    -0.49
    POSITIVE LOGITS
    setVerticalGroup
    0.74
     Италијани
    0.70
     deoarece
    0.69
    Begriffsklä
    0.67
    évaluateur
    0.66
     समीक्षाओं
    0.64
    BeginContext
    0.64
    Geplaatst
    0.63
     समीक्षक
    0.62
    archiviato
    0.62
    Act Density 2.730%

    No Known Activations