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

    Neuronpedia

    INDEX
    Explanations

    the word "that" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     VES
    -0.75
     Eug
    -0.67
    ed
    -0.66
    ร์
    -0.65
     Guadeloupe
    -0.65
     VOS
    -0.64
     Magi
    -0.63
    vements
    -0.63
     Maverick
    -0.63
     SAB
    -0.61
    POSITIVE LOGITS
    that
    1.69
     that
    1.58
    THAT
    1.53
     THAT
    1.46
     That
    1.44
    That
    1.43
     bahawa
    1.05
     bahwa
    0.98
    thats
    0.96
    migrationBuilder
    0.95
    Act Density 0.545%

    No Known Activations