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

    Neuronpedia

    INDEX
    Explanations

    phrases related to geographical locations

    oai_token-act-pair · gpt-3.5-turbo

    references to geographical hemispheres

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chard
    -0.92
    DER
    -0.85
    DH
    -0.75
    MU
    -0.73
    ERAL
    -0.73
    URI
    -0.72
    armor
    -0.71
    urat
    -0.71
    Cho
    -0.71
    amin
    -0.71
    POSITIVE LOGITS
     hemisphere
    1.31
     Hemisphere
    1.25
     lobe
    1.10
    isphere
    0.99
     lapt
    0.83
     cannabin
    0.81
     illum
    0.79
     Scrolls
    0.77
     toile
    0.76
     swoop
    0.74
    Act Density 0.005%

    No Known Activations