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
     vc
    -0.60
    mer
    -0.59
    vements
    -0.58
    าศ
    -0.57
     kms
    -0.57
     Clippers
    -0.56
    淆
    -0.55
     Maverick
    -0.55
    塁
    -0.54
     estn
    -0.54
    POSITIVE LOGITS
    THAT
    1.73
     That
    1.61
    that
    1.60
     THAT
    1.58
    That
    1.56
     that
    1.36
    Thats
    1.06
    thats
    1.05
    脚注の使い方
    1.02
    tvguidetime
    0.96
    Act Density 0.569%

    No Known Activations