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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases or clauses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erli
    -0.17
    رÛĮÙģ
    -0.16
    odable
    -0.16
    ongan
    -0.16
    asu
    -0.15
    iang
    -0.15
    letic
    -0.15
    ÑģÑĤÑİ
    -0.15
    atat
    -0.15
    gnu
    -0.15
    POSITIVE LOGITS
     otherwise
    0.47
    otherwise
    0.37
     specifically
    0.35
     explicitly
    0.33
     Otherwise
    0.33
     OTHERWISE
    0.33
     expressly
    0.32
    Otherwise
    0.31
     stated
    0.26
     noted
    0.25
    Act Density 0.035%

    No Known Activations