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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "flex" in the text

    oai_token-act-pair · gpt-3.5-turbo

    words related to physical strength or flexibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Gore
    -0.84
     Columb
    -0.71
     Alma
    -0.64
    FORE
    -0.63
    keepers
    -0.62
    MAL
    -0.62
     Peninsula
    -0.61
     Hurricanes
    -0.60
    uk
    -0.59
    keeping
    -0.59
    POSITIVE LOGITS
     flex
    1.45
    ibly
    1.22
    itime
    1.17
    ibilities
    1.17
    flex
    1.01
     tremend
    0.95
     horizont
    0.93
    ible
    0.91
    ibility
    0.91
    odox
    0.83
    Act Density 0.004%

    No Known Activations