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

    Neuronpedia

    INDEX
    Explanations

    expressions that summarize or critique ideas and arguments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Brush
    -0.15
    iguous
    -0.15
    enk
    -0.14
    ÑģÑĤан
    -0.14
     Byl
    -0.14
     leh
    -0.14
     McKay
    -0.13
    auer
    -0.13
     ÎŃν
    -0.13
    ô
    -0.13
    POSITIVE LOGITS
     exactly
    0.21
     spot
    0.18
     Amen
    0.17
     point
    0.17
     nicely
    0.16
     precisely
    0.16
    spot
    0.15
     cog
    0.15
     points
    0.15
    ewise
    0.15
    Act Density 0.230%

    No Known Activations