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

    Neuronpedia

    INDEX
    Explanations

    references to islands and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    odom
    -0.17
    ariat
    -0.16
     Gür
    -0.15
    orest
    -0.15
    lok
    -0.15
    river
    -0.14
    753
    -0.14
    essen
    -0.14
    jax
    -0.14
    TEL
    -0.14
    POSITIVE LOGITS
     island
    0.86
     islands
    0.79
     Island
    0.75
     Islands
    0.70
    å²Ľ
    0.58
    島
    0.58
     Islanders
    0.55
     оÑģÑĤÑĢов
    0.51
     ìĦ¬
    0.45
     جز
    0.43
    Act Density 0.209%

    No Known Activations