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

    Neuronpedia

    INDEX
    Explanations

    references to authors and their works in citation formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bulb
    -0.41
    mtrl
    -0.40
    __()
    -0.40
    %");
    -0.39
    "])
    -0.38
    IUrlHelper
    -0.37
    SourceChecksum
    -0.37
    awtextra
    -0.36
    seed
    -0.36
    :"",
    -0.36
    POSITIVE LOGITS
     CURIAM
    0.78
     Exactos
    0.56
    łaszcza
    0.56
    ArgsConstructor
    0.56
    ühungen
    0.54
     betweenstory
    0.52
    gazione
    0.52
    Else
    0.50
    Fordítás
    0.50
     samlet
    0.49
    Act Density 0.199%

    No Known Activations