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

    Neuronpedia

    INDEX
    Explanations

    phrases related to judgment or criticism

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and phrases indicating more complex or compound statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Picks
    -0.69
     Doodle
    -0.66
    itivity
    -0.66
    activity
    -0.65
    anza
    -0.65
    haven
    -0.63
     Catch
    -0.62
    TF
    -0.62
     Skip
    -0.61
    ny
    -0.60
    POSITIVE LOGITS
     interrogated
    1.15
     executed
    1.08
     photographed
    1.06
     transported
    1.06
     punished
    1.06
     repaired
    1.04
     rewarded
    1.04
     evaluated
    1.04
     prosecuted
    1.04
     reused
    1.03
    Act Density 0.268%

    No Known Activations