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

    Neuronpedia

    INDEX
    Explanations

    names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    punctuation, particularly commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olves
    -0.77
    adh
    -0.67
     outputs
    -0.64
    animate
    -0.61
    versive
    -0.60
    ¥µ
    -0.60
    appropriate
    -0.59
    ole
    -0.59
    FIX
    -0.58
    overs
    -0.57
    POSITIVE LOGITS
     meanwhile
    1.22
     however
    1.15
     flanked
    1.05
    enegger
    1.02
     who
    0.94
     moreover
    0.94
     nicknamed
    0.92
     along
    0.92
     whose
    0.90
     pictured
    0.90
    Act Density 0.125%

    No Known Activations