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
    ãģĤãģ£ãģŁ
    -0.15
    vre
    -0.15
    ãģĬ
    -0.15
    nat
    -0.15
    icens
    -0.14
    uele
    -0.14
    amp
    -0.14
    ned
    -0.14
    sik
    -0.14
    à¹Ģลย
    -0.14
    POSITIVE LOGITS
    ched
    0.19
     they
    0.19
     there
    0.19
    ching
    0.17
     it
    0.17
     we
    0.16
    /how
    0.16
    /if
    0.15
    upon
    0.15
    andalone
    0.14
    Act Density 0.314%

    No Known Activations