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

    Neuronpedia

    INDEX
    Explanations

    specific mentions of the word "condemn" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    conditional phrases and terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kaya
    -0.71
    chy
    -0.66
    ches
    -0.65
     thumbs
    -0.61
     Brilliant
    -0.61
     Lans
    -0.61
    ngth
    -0.59
     Pew
    -0.59
     Werewolf
    -0.58
    DIR
    -0.58
    POSITIVE LOGITS
    ominium
    1.39
    itional
    1.32
    ensed
    1.30
    ensation
    1.29
    enser
    1.26
    uctor
    1.25
    itions
    1.22
    ensing
    1.18
    emn
    1.17
    itionally
    1.11
    Act Density 0.025%

    No Known Activations