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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "this" and related pronouns in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ever
    -0.14
    æ®Ĭ
    -0.14
    oubted
    -0.14
    iT
    -0.14
    iler
    -0.14
    iesz
    -0.14
     lies
    -0.13
    ync
    -0.13
     tersebut
    -0.13
    caf
    -0.13
    POSITIVE LOGITS
     ones
    0.26
     morning
    0.20
    timeofday
    0.19
     reminded
    0.18
     whole
    0.18
    'll
    0.17
    -IS
    0.17
     afternoon
    0.17
     certainly
    0.16
     guy
    0.16
    Act Density 0.212%

    No Known Activations