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

    Neuronpedia

    INDEX
    Explanations

    testimonies related to workplace safety and incidents

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

    Follows a pronoun or short word

    np_acts-logits-general · gemini-2.0-flash

    pronouns and auxiliary verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     comportements
    -0.97
     behavioural
    -0.95
     behaviours
    -0.92
    behaviour
    -0.88
     Behavioural
    -0.86
     vectorielles
    -0.83
     argint
    -0.82
     behaviour
    -0.81
     ledig
    -0.80
    Behaviour
    -0.80
    POSITIVE LOGITS
    GeneratedMessage
    0.64
     تضيفلها
    0.54
     colored
    0.53
     materially
    0.49
     endeavored
    0.49
     endeav
    0.49
     vim
    0.48
     JpaRepository
    0.48
     clase
    0.47
     investis
    0.47
    Act Density 0.784%

    No Known Activations