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

    Neuronpedia

    INDEX
    Explanations

    references to numbers and their mathematical properties

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     olsun
    -0.07
    æŁ±
    -0.06
    -ln
    -0.06
    ',{↵
    -0.06
    aad
    -0.06
    yo
    -0.06
    нимаÑĤÑĮ
    -0.06
    eria
    -0.06
    ',{'
    -0.06
    ฤษ
    -0.06
    POSITIVE LOGITS
    ,
    0.12
    ,↵↵
    0.07
    onz
    0.07
    umlu
    0.07
    434
    0.07
    embro
    0.06
    zilla
    0.06
    ownik
    0.06
    ¸
    0.06
    ird
    0.06
    Act Density 0.269%

    No Known Activations