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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "sure" indicating certainty or assurance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     THEM
    -0.15
    ynchronously
    -0.14
    normally
    -0.14
    him
    -0.14
     eux
    -0.14
    zeigt
    -0.14
     bisher
    -0.14
    ryn
    -0.14
     Worse
    -0.13
    IGO
    -0.13
    POSITIVE LOGITS
     none
    0.29
     everything
    0.28
     there
    0.26
     nothing
    0.26
     nobody
    0.25
     sure
    0.24
     they
    0.24
     everyone
    0.22
     no
    0.21
    everything
    0.20
    Act Density 0.042%

    No Known Activations