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

    Neuronpedia

    INDEX
    Explanations

    words related to routing and paths

    oai_token-act-pair · gpt-3.5-turbo

    terms related to routing and organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    endi
    -0.79
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.78
     Dunham
    -0.71
     Libre
    -0.67
     harb
    -0.67
    ATURE
    -0.67
    minster
    -0.61
    Leaks
    -0.61
    ixels
    -0.61
    éĸ
    -0.60
    POSITIVE LOGITS
     routed
    1.07
     rout
    0.99
     routing
    0.88
    MpServer
    0.87
    ²¾
    0.82
    ahime
    0.81
    xual
    0.79
    htaking
    0.79
    heastern
    0.77
    oute
    0.76
    Act Density 0.019%

    No Known Activations