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

    Neuronpedia

    INDEX
    Explanations

    instances of actions and events related to submissions or requests

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

    frequent / regularly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     оригіналу
    -0.62
     חיצוניים
    -0.60
     שוליים
    -0.60
     ProtoMessage
    -0.56
    GrantedAuthority
    -0.55
     CreateTagHelper
    -0.53
    AndEndTag
    -0.52
    brities
    -0.52
     jagung
    -0.52
     Picchu
    -0.50
    POSITIVE LOGITS
     frequent
    0.44
     regularly
    0.43
     brukar
    0.41
     frequently
    0.41
     регулярно
    0.40
     regelmäßig
    0.38
     monthly
    0.38
    frequently
    0.38
    frequent
    0.36
     regularmente
    0.35
    Act Density 0.405%

    No Known Activations