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

    Neuronpedia

    INDEX
    Explanations

    themes of deception and appearance versus reality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     cif
    -0.15
    isay
    -0.15
    enek
    -0.15
     paternal
    -0.15
    /backend
    -0.15
     Kil
    -0.15
     <+
    -0.14
    peats
    -0.14
    DW
    -0.14
    iline
    -0.14
    POSITIVE LOGITS
    (*)(
    0.19
    onth
    0.17
    uppy
    0.15
    779
    0.14
     ÙĨب
    0.14
     Expert
    0.14
    lice
    0.14
    apor
    0.14
     à¤ĸर
    0.14
    488
    0.14
    Act Density 0.170%

    No Known Activations