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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "in" and its contextual variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     in
    -0.23
    åľ¨
    -0.20
    stown
    -0.19
    InView
    -0.17
    iness
    -0.17
    اÙĨÙĩ
    -0.16
    /Area
    -0.16
    edin
    -0.15
    arme
    -0.15
    inka
    -0.14
    POSITIVE LOGITS
    wards
    0.30
    /out
    0.30
    [to
    0.26
    shore
    0.23
    ot
    0.23
    animate
    0.17
    -between
    0.17
    WARDS
    0.17
    quis
    0.17
    /up
    0.17
    Act Density 0.091%

    No Known Activations