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

    Neuronpedia

    INDEX
    Explanations

    pronouns and their corresponding verb forms within the context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     الرياضيه
    -0.87
     Autorizaciones
    -0.77
    ^(@)
    -0.69
     microfilm
    -0.67
     שוליים
    -0.63
    werpen
    -0.61
     אחרים
    -0.58
    alga
    -0.58
    veloppe
    -0.57
    Hentet
    -0.57
    POSITIVE LOGITS
     незавершена
    0.67
     lenker
    0.59
     transfieras
    0.55
    ::::::::
    0.52
    __':
    0.50
    sort
    0.49
    はどこ
    0.48
     picioare
    0.47
    napp
    0.47
     Computation
    0.47
    Act Density 0.720%

    No Known Activations