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

    Neuronpedia

    INDEX
    Explanations

    expressions of uncertainty or speculation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Probably
    -0.17
     zÅĻejmÄĽ
    -0.15
     probably
    -0.15
     Apparently
    -0.15
    probably
    -0.15
     muht
    -0.15
     reportedly
    -0.15
     Basically
    -0.14
     обÑĭÑĩно
    -0.14
    licer
    -0.14
    POSITIVE LOGITS
     even
    0.26
     because
    0.22
     none
    0.22
     some
    0.22
     not
    0.22
     it
    0.21
     something
    0.20
     someone
    0.20
     more
    0.19
     they
    0.19
    Act Density 0.055%

    No Known Activations