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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "there" to indicate locations or existence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sth
    -0.18
    venes
    -0.17
    ói
    -0.16
    usto
    -0.15
    ttp
    -0.15
    »
    -0.15
    abe
    -0.15
    chia
    -0.14
    enny
    -0.14
    amel
    -0.14
    POSITIVE LOGITS
     dort
    0.16
    alone
    0.15
    ìĦľ
    0.15
     alone
    0.15
     they
    0.14
    after
    0.14
    ision
    0.14
    ison
    0.13
    ec
    0.13
    siz
    0.13
    Act Density 0.052%

    No Known Activations