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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "that" and related pronouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Naw
    -0.17
     indirectly
    -0.16
    anson
    -0.15
    utc
    -0.15
     trans
    -0.15
    rans
    -0.14
     Hier
    -0.14
     Harr
    -0.14
     Bias
    -0.14
     Cape
    -0.14
    POSITIVE LOGITS
    .ud
    0.17
    kee
    0.16
    chia
    0.16
    ç´
    0.16
    setChecked
    0.15
    RYPTO
    0.15
     Hüs
    0.15
    semicolon
    0.15
    porte
    0.15
    comb
    0.15
    Act Density 0.024%

    No Known Activations