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

    Neuronpedia

    INDEX
    Explanations

    numerical identifiers and programming concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     T
    -0.19
     A
    -0.18
     D
    -0.18
     C
    -0.17
     S
    -0.17
     B
    -0.17
     M
    -0.17
     In
    -0.17
     P
    -0.17
     F
    -0.17
    POSITIVE LOGITS
    ,
    1.11
    ,↵
    0.65
    ,↵↵
    0.48
    ,č↵
    0.41
     ,
    0.40
    ,...↵
    0.38
    ®,
    0.37
    ี,
    0.36
    ,[
    0.36
    ,\↵
    0.34
    Act Density 0.494%

    No Known Activations