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

    Neuronpedia

    INDEX
    Explanations

    locations or directions within geographical regions

    oai_token-act-pair · gpt-3.5-turbo

    directional references related to geographical locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    events
    -0.77
    nikov
    -0.74
    apply
    -0.73
    earth
    -0.73
    ipedia
    -0.72
    urious
    -0.71
    ontent
    -0.71
    Money
    -0.71
    ute
    -0.69
    ======
    -0.69
    POSITIVE LOGITS
    most
    1.65
     portion
    1.30
     hemisphere
    1.27
     edge
    1.23
     tip
    1.18
     part
    1.15
     flank
    1.13
     side
    1.12
     extrem
    1.11
     periphery
    1.09
    Act Density 0.084%

    No Known Activations