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

    Neuronpedia

    INDEX
    Explanations

    words related to toxicity and wellness

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "totally" and other related terms indicating totality or completeness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     symmetry
    -0.66
     slideshow
    -0.66
     grace
    -0.65
     lur
    -0.65
     fixing
    -0.64
     Militia
    -0.62
     strat
    -0.61
     cues
    -0.61
     riff
    -0.60
     page
    -0.60
    POSITIVE LOGITS
    otally
    3.44
    otal
    2.08
    alks
    1.87
    oxic
    1.81
    ogether
    1.65
    ruly
    1.58
    ruck
    1.49
    angible
    1.46
    OTAL
    1.45
    initely
    1.38
    Act Density 0.045%

    No Known Activations