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

    Neuronpedia

    INDEX
    Explanations

    terms related to "counterfactual" scenarios or discussions in causal inference

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NgModule
    -0.82
    glVertex
    -0.80
    ✨:
    -0.79
    **/
    -0.77
    verläs
    -0.74
    gnition
    -0.72
     récomp
    -0.72
     tourné
    -0.71
     placés
    -0.71
     AssemblyVersion
    -0.70
    POSITIVE LOGITS
     counter
    2.59
     Counter
    2.56
     COUNTER
    2.35
     counters
    2.33
    counter
    2.29
    Counter
    2.28
     Counters
    2.17
    COUNTER
    2.06
    counters
    1.80
    Counters
    1.76
    Act Density 0.070%

    No Known Activations