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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases indicating uncertainty or hypothetical scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sẵn
    -0.15
     sobie
    -0.15
    (named
    -0.15
    akov
    -0.14
     Dude
    -0.14
    ÐĴÑĤ
    -0.14
    lington
    -0.13
    qual
    -0.13
     safest
    -0.13
     quickest
    -0.13
    POSITIVE LOGITS
     done
    0.31
     compared
    0.28
     viewed
    0.27
     taken
    0.26
     used
    0.26
     applied
    0.24
    done
    0.24
     properly
    0.22
     accompanied
    0.22
     Done
    0.22
    Act Density 0.112%

    No Known Activations