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

    Neuronpedia

    INDEX
    Explanations

    references to counting or numerical operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    glVertex
    -0.85
    NgModule
    -0.81
     récomp
    -0.79
    gnition
    -0.78
    ✨:
    -0.77
     placés
    -0.76
     esempi
    -0.75
     fédé
    -0.73
    ?\
    -0.72
    verläs
    -0.72
    POSITIVE LOGITS
     counter
    2.32
     Counter
    2.29
     counters
    2.13
     COUNTER
    2.09
    counter
    2.03
    Counter
    2.01
     Counters
    1.95
    COUNTER
    1.87
    counters
    1.69
    Counters
    1.59
    Act Density 0.053%

    No Known Activations