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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "just."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ίοÏĤ
    -0.15
    Ïĩι
    -0.15
    ishly
    -0.15
    urator
    -0.15
    anlık
    -0.14
    cko
    -0.14
    yps
    -0.13
    ALLY
    -0.13
    ÄĽst
    -0.13
    antd
    -0.13
    POSITIVE LOGITS
    ices
    0.29
    ice
    0.24
    icia
    0.23
    ICE
    0.23
    ification
    0.23
    iciar
    0.22
    icial
    0.22
    ified
    0.22
    iciary
    0.21
    itia
    0.20
    Act Density 0.024%

    No Known Activations