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

    Neuronpedia

    INDEX
    Explanations

    co-occurrence of the conjunction "and" within sentences

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Picks
    -0.76
     Doodle
    -0.66
    anza
    -0.65
     Pinball
    -0.63
    activity
    -0.61
     Catch
    -0.61
    ENSE
    -0.61
    eness
    -0.60
    TF
    -0.60
    NP
    -0.59
    POSITIVE LOGITS
     executed
    1.15
     repaired
    1.15
     interrogated
    1.14
     photographed
    1.12
     reused
    1.09
     analyzed
    1.08
     transported
    1.07
     evaluated
    1.07
     tested
    1.06
     prosecuted
    1.05
    Act Density 0.225%

    No Known Activations