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

    Neuronpedia

    INDEX
    Explanations

    verbs indicating actions and outcomes in a narrative context

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

    Follows verbs expressing intent or process

    np_acts-logits-general · gemini-2.0-flash

    what will or did happen

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    __':
    -0.73
    __":
    -0.68
     NSCoder
    -0.61
    BASEPATH
    -0.60
     незавершена
    -0.56
    ]--;
    -0.55
     ArrayAdapter
    -0.55
    RectangleBorder
    -0.54
     sessionFactory
    -0.53
     Eurosport
    -0.53
    POSITIVE LOGITS
     exactamente
    0.78
     versus
    0.69
     originalmente
    0.69
     ultimately
    0.68
     esattamente
    0.68
     exactement
    0.67
     وما
    0.66
     overall
    0.64
     determines
    0.63
     exactly
    0.60
    Act Density 0.354%

    No Known Activations