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

    Neuronpedia

    INDEX
    Explanations

    code structures and functions in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    	RTE
    -0.17
    bes
    -0.14
    æĺ
    -0.14
    ait
    -0.14
    illac
    -0.13
    ennes
    -0.13
    AIT
    -0.13
    ucch
    -0.13
    /Observable
    -0.13
     Ùħض
    -0.13
    POSITIVE LOGITS
     defer
    0.33
    defer
    0.29
     var
    0.28
     _,
    0.25
     err
    0.25
    var
    0.24
    	var
    0.22
    -var
    0.20
    	defer
    0.19
     deferred
    0.18
    Act Density 0.022%

    No Known Activations