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

    Neuronpedia

    INDEX
    Explanations

    terms related to objects and their properties in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    GraphicsUnit
    -0.52
     It
    -0.47
    amp
    -0.47
     Why
    -0.46
    von
    -0.46
     приходи
    -0.46
    va
    -0.45
     _:
    -0.44
    oline
    -0.44
    om
    -0.43
    POSITIVE LOGITS
    Obj
    2.00
     Obj
    1.99
    obj
    1.87
     Objective
    1.86
     obj
    1.85
     Object
    1.84
    Objective
    1.79
    Object
    1.72
    OBJ
    1.72
     object
    1.66
    Act Density 0.169%

    No Known Activations