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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases and expressions of uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     either
    -0.32
     Either
    -0.28
    either
    -0.28
     EITHER
    -0.26
     indeed
    -0.26
    Either
    -0.26
     instead
    -0.21
     Indeed
    -0.20
     anytime
    -0.19
    Indeed
    -0.18
    POSITIVE LOGITS
     seemingly
    0.20
     sometimes
    0.20
    Sometimes
    0.18
     slight
    0.18
     smallest
    0.18
     olmayan
    0.17
     slightly
    0.17
     nomin
    0.16
     seeming
    0.16
     otherwise
    0.16
    Act Density 0.135%

    No Known Activations