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

    Neuronpedia

    INDEX
    Explanations

    short strings that include the word "work" as a part of a larger word or name

    oai_token-act-pair · gpt-3.5-turbo

    repeated instances of the term 'ork' in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ples
    -0.75
     tradem
    -0.65
    cit
    -0.62
     vanilla
    -0.61
     cardio
    -0.59
     charity
    -0.58
     behavi
    -0.58
    ciples
    -0.57
    EVA
    -0.56
    cence
    -0.56
    POSITIVE LOGITS
    ansas
    1.15
    hire
    0.94
    ozy
    0.91
    lift
    0.89
    patrick
    0.85
    osaurus
    0.84
    enhagen
    0.82
    ork
    0.81
    atana
    0.80
    owski
    0.80
    Act Density 0.004%

    No Known Activations