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

    Neuronpedia

    INDEX
    Explanations

    instances of objects in code or technical documentation

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

    Object Role Modeling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GEBURTS
    -0.67
     незавершена
    -0.48
     оригіналу
    -0.46
     thirst
    -0.46
    atisfied
    -0.45
    zarchiwizowane
    -0.44
    Viitteet
    -0.44
    󠁣
    -0.44
    endpush
    -0.43
    afety
    -0.43
    POSITIVE LOGITS
    Object
    2.20
     Object
    1.65
    OBJECT
    1.11
    Objects
    1.00
     OBJECT
    0.93
     Objects
    0.90
    bject
    0.85
    ObjectName
    0.79
    ToObject
    0.79
    Objeto
    0.79
    Act Density 0.011%

    No Known Activations