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

    Neuronpedia

    INDEX
    Explanations

    references to twins or twin-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     صوتيه
    -0.96
    enumii
    -0.77
    zież
    -0.74
     Chhattisgarh
    -0.72
     Mahomet
    -0.72
    okovic
    -0.72
     Czechos
    -0.71
     AppBar
    -0.70
     coq
    -0.70
     Solano
    -0.69
    POSITIVE LOGITS
     twin
    3.18
     Twin
    3.04
    Twin
    2.95
    twin
    2.78
     twins
    2.63
     Twins
    2.40
    Twins
    2.27
    ツイン
    1.47
    孪
    1.31
     ツイン
    1.26
    Act Density 0.080%

    No Known Activations