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

    Neuronpedia

    INDEX
    Explanations

    the word "that" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aan
    -0.18
    ovan
    -0.17
    oop
    -0.16
    usa
    -0.15
     Stat
    -0.15
     crowds
    -0.14
    arus
    -0.14
    overe
    -0.14
    Stat
    -0.14
    (char
    -0.13
    POSITIVE LOGITS
    heimer
    0.17
     net
    0.15
    nets
    0.15
    adaki
    0.14
     Net
    0.14
    arken
    0.14
    ruba
    0.14
    lient
    0.14
    ackers
    0.14
     nets
    0.13
    Act Density 0.019%

    No Known Activations