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

    Neuronpedia

    INDEX
    Explanations

    locations or directions (north, south, east, west) mentioned in conjunction with each other

    oai_token-act-pair · gpt-3.5-turbo

    references to geographical directions, particularly west and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    angu
    -0.64
     surrender
    -0.63
    cci
    -0.63
     Wee
    -0.63
    sett
    -0.63
     Sap
    -0.62
    Maker
    -0.61
     Coh
    -0.61
     Likes
    -0.60
    NAS
    -0.60
    POSITIVE LOGITS
    west
    1.04
    eus
    0.85
    east
    0.83
    rup
    0.80
    orea
    0.78
    agascar
    0.77
    iate
    0.77
    wards
    0.77
    ragon
    0.76
    ãĤ´ãĥ³
    0.75
    Act Density 0.021%

    No Known Activations