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

    Neuronpedia

    INDEX
    Explanations

    locations or places within a text

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    rolet
    -0.90
    jad
    -0.89
    ³³³³³³³³
    -0.86
    ets
    -0.82
    hya
    -0.81
     franc
    -0.75
    urally
    -0.75
    ouf
    -0.75
    astical
    -0.74
    sson
    -0.74
    POSITIVE LOGITS
    upon
    1.40
    abouts
    1.22
    soever
    1.15
    fore
    0.95
     they
    0.84
    OULD
    0.82
    bos
    0.81
    chwitz
    0.80
    igham
    0.80
     [|
    0.79
    Act Density 0.596%

    No Known Activations