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

    Neuronpedia

    INDEX
    Explanations

    phrases related to being physically outside of a specific location

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "out."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gemony
    -0.80
    ĪĴ
    -0.70
     mosaic
    -0.64
     subp
    -0.64
    eways
    -0.62
     Genocide
    -0.62
    erity
    -0.61
    encies
    -0.60
     abhor
    -0.59
    apses
    -0.59
    POSITIVE LOGITS
    fitted
    1.26
     partying
    1.01
    doing
    1.00
    raged
    0.96
    ranged
    0.96
    done
    0.95
     celebrating
    0.92
    fed
    0.90
    stretched
    0.89
    fitting
    0.88
    Act Density 0.135%

    No Known Activations