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

    Neuronpedia

    INDEX
    Explanations

    specific phrases that indicate exceptions, comparisons, or critical conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zig
    -0.15
    irc
    -0.15
    Assertions
    -0.15
    iges
    -0.14
    yc
    -0.14
    á»Ńa
    -0.14
    uento
    -0.14
    ause
    -0.14
    ÅĤa
    -0.14
    laughter
    -0.13
    POSITIVE LOGITS
     physical
    0.25
     Physical
    0.21
    physical
    0.21
     aspect
    0.19
    Physical
    0.17
     regarding
    0.17
     od
    0.17
     fÃŃs
    0.16
    phis
    0.16
     hardware
    0.16
    Act Density 0.150%

    No Known Activations