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

    Neuronpedia

    INDEX
    Explanations

    phrases starting with "that" indicating emphasis or importance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RepeatedField
    -0.60
     with
    -0.55
    ึกษา
    -0.55
     wikipagina
    -0.54
     and
    -0.53
    клопе
    -0.53
     Çünkü
    -0.53
     Comentarios
    -0.52
     cek
    -0.49
     dictionnaire
    -0.48
    POSITIVE LOGITS
     That
    0.86
    UNSIGNED
    0.82
    That
    0.82
     wasn
    0.82
     ought
    0.78
    THAT
    0.78
    leby
    0.77
     wouldn
    0.77
    脚注の使い方
    0.77
    copg
    0.75
    Act Density 0.067%

    No Known Activations