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

    Neuronpedia

    INDEX
    Explanations

    phrases related to exclusivity or singularity

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "only" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    insula
    -0.84
    arted
    -0.64
    idon
    -0.62
     Massive
    -0.61
     heterogeneity
    -0.58
    went
    -0.58
     fragmentation
    -0.58
    finder
    -0.57
     Mages
    -0.56
    --------------------------------------------------------
    -0.55
    POSITIVE LOGITS
     marginally
    0.86
     incidentally
    0.79
     only
    0.70
     omit
    0.65
    ļéĨĴ
    0.63
     barely
    0.62
    rama
    0.61
    onso
    0.61
     ONLY
    0.61
     sparing
    0.60
    Act Density 0.070%

    No Known Activations