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

    Neuronpedia

    INDEX
    Explanations

    the word "that" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     PHA
    -0.60
    mer
    -0.57
     Royce
    -0.56
     vif
    -0.53
     Magi
    -0.52
     MV
    -0.52
     Trimble
    -0.51
     tanong
    -0.50
    塁
    -0.50
    vements
    -0.49
    POSITIVE LOGITS
    THAT
    1.69
     That
    1.62
    That
    1.60
     THAT
    1.56
    that
    1.55
     that
    1.34
     ese
    1.06
    thats
    1.05
    Thats
    1.01
    this
    0.99
    Act Density 0.572%

    No Known Activations