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

    Neuronpedia

    INDEX
    Explanations

    specific identifiers or codes related to routing

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    rungsseite
    -1.05
     resourceCulture
    -1.04
    wahati
    -1.02
     CreateTagHelper
    -0.97
    تقاوى
    -0.94
    原始内容存档于
    -0.88
    AccessFile
    -0.87
    featureID
    -0.86
    évaluateur
    -0.85
    igshid
    -0.85
    POSITIVE LOGITS
    |-
    1.06
     |-
    0.86
     rem
    0.65
    |--
    0.59
    centred
    0.59
    imme
    0.58
     Garg
    0.57
    Γ
    0.56
     Tos
    0.55
    ён
    0.54
    Act Density 0.001%

    No Known Activations