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

    Neuronpedia

    INDEX
    Explanations

    instances of specific object types in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     سكانية
    -0.90
     enfans
    -0.86
     auffi
    -0.80
     }</
    -0.79
     históricas
    -0.77
     transfieras
    -0.76
     iſt
    -0.76
     saites
    -0.76
    tagHelperRunner
    -0.76
     argint
    -0.75
    POSITIVE LOGITS
    의
    0.98
     Yang
    0.97
    Yang
    0.89
     yang
    0.78
     의
    0.69
    yang
    0.68
     YANG
    0.66
     instanceof
    0.65
     המ
    0.63
     yg
    0.56
    Act Density 0.015%

    No Known Activations