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

    Neuronpedia

    INDEX
    Explanations

    stories about personal experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Context after common words

    np_acts-logits-general · gemini-2.0-flash

    overheard / happened events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autant
    -0.72
    éndolo
    -0.64
     Réponses
    -0.61
     dále
    -0.59
    ])).
    -0.59
     bisherigen
    -0.58
    を選択します
    -0.58
    ]));
    -0.56
    現在は
    -0.56
     Сегодня
    -0.56
    POSITIVE LOGITS
     someone
    0.84
    someone
    0.81
    Someone
    0.81
     somebody
    0.77
    某
    0.73
     overheard
    0.73
     recently
    0.71
    Somebody
    0.70
     accidentally
    0.70
     somewhere
    0.68
    Act Density 0.514%

    No Known Activations