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

    Neuronpedia

    INDEX
    Explanations

    conditional or hypothetical phrases that indicate uncertainty or speculative reasoning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ourselves
    -0.17
     loro
    -0.15
    ardır
    -0.14
     eux
    -0.14
    them
    -0.14
    mess
    -0.13
    Ĵáŀ
    -0.13
    alse
    -0.13
    imeo
    -0.13
     __("
    -0.13
    POSITIVE LOGITS
     there
    0.39
    there
    0.30
     certain
    0.22
     THERE
    0.22
     they
    0.21
    /if
    0.19
     some
    0.19
     it
    0.18
     only
    0.18
    There
    0.18
    Act Density 0.517%

    No Known Activations