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

    the word "where" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TE
    -0.68
    bite
    -0.66
    TEXT
    -0.64
    SIGN
    -0.63
    icit
    -0.63
    TAG
    -0.63
    apult
    -0.62
    ifest
    -0.62
    mask
    -0.61
    ulatory
    -0.61
    POSITIVE LOGITS
    upon
    1.41
    soever
    0.96
    abouts
    0.93
    fore
    0.92
    arton
    0.75
     birthplace
    0.69
    izens
    0.69
     temperatures
    0.65
     they
    0.64
    anwhile
    0.64
    Act Density 0.050%

    No Known Activations