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

    Neuronpedia

    INDEX
    Explanations

    locations or places mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "anywhere."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    estamp
    -0.68
    alion
    -0.68
    eme
    -0.65
    prem
    -0.64
     Reef
    -0.63
    zai
    -0.62
    rett
    -0.62
    ãĥīãĥ©
    -0.61
    76561
    -0.60
    hift
    -0.59
    POSITIVE LOGITS
     else
    1.63
    abouts
    1.29
     Else
    1.13
    Else
    1.05
     near
    1.03
    where
    0.94
    near
    0.93
    else
    0.92
     Near
    0.86
    side
    0.74
    Act Density 0.055%

    No Known Activations