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

    Neuronpedia

    INDEX
    Explanations

    references to licensing and attribution in creative works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pere
    -0.15
     unc
    -0.15
     real
    -0.15
    ofs
    -0.15
     Ross
    -0.14
    iso
    -0.14
     Lines
    -0.14
     Quang
    -0.14
    965
    -0.14
    ington
    -0.14
    POSITIVE LOGITS
    /legal
    0.17
    emek
    0.15
    书记
    0.15
    neas
    0.15
    ripp
    0.15
    ALSE
    0.15
    ÅĤaw
    0.14
     seins
    0.14
    yleft
    0.14
    inkel
    0.14
    Act Density 0.064%

    No Known Activations