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

    Neuronpedia

    INDEX
    Explanations

    mentions of conflicts or confrontations involving people and actions (such as wrestle, punch, defend) among various individuals

    oai_token-act-pair · gpt-3.5-turbo

    frequent punctuation marks, particularly commas, in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eco
    -0.69
    pec
    -0.68
    ire
    -0.63
    rid
    -0.62
    EngineDebug
    -0.62
    overs
    -0.62
    ridges
    -0.61
    ©¶æ
    -0.61
     outputs
    -0.61
    mos
    -0.60
    POSITIVE LOGITS
     whom
    1.33
    who
    1.14
     who
    1.05
    whose
    1.03
     whose
    0.99
     Jr
    0.96
     aka
    0.84
     Sr
    0.83
     although
    0.83
    Jr
    0.82
    Act Density 0.366%

    No Known Activations