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

    Neuronpedia

    INDEX
    Explanations

    numerical values or counts in the text

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ']]
    -0.59
    ']")
    -0.57
    "}")
    -0.57
    Przypisy
    -0.56
    TabIndex
    -0.55
    ']))
    -0.54
    ')")
    -0.54
     apologise
    -0.53
     Kini
    -0.53
    "])){
    -0.53
    POSITIVE LOGITS
    +#+#
    0.75
    EndContext
    0.65
     htons
    0.55
     للمعارف
    0.54
     règlement
    0.54
    RTCF
    0.53
    스템
    0.52
     declarat
    0.52
    sig
    0.51
    DeleteBehavior
    0.50
    Act Density 0.019%

    No Known Activations