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

    Neuronpedia

    INDEX
    Explanations

    phrases related to progressive and innovative thinking

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kö
    -0.18
    pector
    -0.17
    olie
    -0.16
    Ìģc
    -0.15
    askell
    -0.15
    êu
    -0.15
    iber
    -0.14
    pecially
    -0.14
    MUX
    -0.14
    riad
    -0.14
    POSITIVE LOGITS
    /back
    0.35
    -thinking
    0.31
    -facing
    0.29
    ward
    0.29
    ly
    0.28
    -looking
    0.28
    wards
    0.28
    /down
    0.28
    -leaning
    0.24
    most
    0.24
    Act Density 0.049%

    No Known Activations