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

    Neuronpedia

    INDEX
    Explanations

    locations or places

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "where."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unch
    -0.70
    ve
    -0.63
    bite
    -0.62
    icit
    -0.61
    strap
    -0.60
    spect
    -0.60
     squeeze
    -0.59
    rolet
    -0.59
    ]);
    -0.58
    SIGN
    -0.58
    POSITIVE LOGITS
    upon
    1.51
    fore
    1.00
    soever
    0.98
    abouts
    0.98
    ãĥ¯ãĥ³
    0.70
    izens
    0.68
    acan
    0.68
    abama
    0.67
    arton
    0.66
     birthplace
    0.66
    Act Density 0.041%

    No Known Activations