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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating possibility or uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     presumably
    -0.30
     probably
    -0.29
     apparently
    -0.27
    probably
    -0.25
     Probably
    -0.24
     undoubtedly
    -0.24
     reportedly
    -0.23
     surely
    -0.23
     evidently
    -0.23
     zÅĻejmÄĽ
    -0.22
    POSITIVE LOGITS
     someday
    0.26
     even
    0.23
     slightly
    0.20
     TOO
    0.19
    /pro
    0.19
     better
    0.19
     sogar
    0.18
     some
    0.18
     best
    0.17
     too
    0.17
    Act Density 0.230%

    No Known Activations