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

    Neuronpedia

    INDEX
    Explanations

    expressions related to comparisons and evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -0.77
    saurus
    -0.74
    yntaxException
    -0.68
     fathoms
    -0.68
    PhysRev
    -0.68
    Попис
    -0.66
    rungsseite
    -0.66
    )•
    -0.66
     تانيه
    -0.66
    PerformLayout
    -0.63
    POSITIVE LOGITS
    the
    0.79
    these
    0.64
     THESE
    0.63
     THE
    0.61
    their
    0.60
     an
    0.58
    many
    0.54
    your
    0.53
     these
    0.53
     their
    0.52
    Act Density 0.470%

    No Known Activations