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

    Neuronpedia

    INDEX
    Explanations

    phrases related to possession or experiences over time

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

    "Has/have been" construction

    np_acts-logits-general · gemini-2.0-flash

    had been

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     térm
    -0.58
    scribe
    -0.56
     ratify
    -0.56
     recupero
    -0.55
     realisation
    -0.53
     promesse
    -0.53
     recovers
    -0.50
    declare
    -0.49
    rain
    -0.48
     attains
    -0.48
    POSITIVE LOGITS
    ########.
    0.77
    "):
    0.70
     CreateTagHelper
    0.68
     actually
    0.67
    XmlAccessType
    0.66
     been
    0.64
    onActivityResult
    0.63
    BufferException
    0.63
     also
    0.60
    '):
    0.60
    Act Density 0.281%

    No Known Activations