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

    Neuronpedia

    INDEX
    Explanations

    references to physical or metaphorical poles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÙĨا
    -0.18
     Airways
    -0.16
    nat
    -0.16
    à¹Ģà¸ķ
    -0.16
    æĺĮ
    -0.15
    emetery
    -0.14
    ilestone
    -0.14
    azine
    -0.14
    776
    -0.14
    ÑĤии
    -0.14
    POSITIVE LOGITS
    pole
    0.25
     Pole
    0.24
     pole
    0.23
    axed
    0.21
    mic
    0.21
    cat
    0.19
     position
    0.19
     vault
    0.18
    star
    0.18
     poles
    0.18
    Act Density 0.009%

    No Known Activations