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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating conditionality or exceptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iang
    -0.16
    izable
    -0.16
     Elo
    -0.15
    ÅĤÄħ
    -0.15
    atat
    -0.14
    gnu
    -0.14
    iaÅĤa
    -0.13
    enberg
    -0.13
    ochen
    -0.13
    warning
    -0.13
    POSITIVE LOGITS
     otherwise
    0.38
    otherwise
    0.29
     OTHERWISE
    0.29
     noted
    0.28
     stated
    0.28
     Otherwise
    0.26
     specifically
    0.26
     expressly
    0.25
     explicitly
    0.24
     indicated
    0.23
    Act Density 0.035%

    No Known Activations