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

    Neuronpedia

    INDEX
    Explanations

    phrases related to criminal activities and investigations

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tro
    -0.68
    FIX
    -0.67
    manac
    -0.62
     prompt
    -0.61
    ital
    -0.61
     experience
    -0.59
    pac
    -0.58
    EngineDebug
    -0.58
     opp
    -0.58
    Parameters
    -0.58
    POSITIVE LOGITS
     Jr
    1.26
     Sr
    1.13
     aka
    1.02
     whom
    1.00
     who
    0.99
    Jr
    0.96
     whose
    0.94
    who
    0.91
    whose
    0.83
     pictured
    0.79
    Act Density 0.375%

    No Known Activations