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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "qu" or related terms signifying questioning or uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    o
    -0.26
    an
    -0.19
    oje
    -0.18
    ailles
    -0.18
    ugi
    -0.17
    oq
    -0.17
    andi
    -0.16
    i
    -0.16
    oÄį
    -0.16
    olet
    -0.15
    POSITIVE LOGITS
    ench
    0.25
    izz
    0.22
    ies
    0.22
    irk
    0.21
     qu
    0.20
    able
    0.20
    eso
    0.19
    asic
    0.19
    esion
    0.19
    ashed
    0.18
    Act Density 0.010%

    No Known Activations