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

    Neuronpedia

    INDEX
    Explanations

    the preposition "in" and its various contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     *((
    -0.57
     nød
    -0.56
     chô
    -0.55
     excès
    -0.55
    seamnă
    -0.54
    neté
    -0.52
    hoeddwyd
    -0.51
     Wikimedijinoj
    -0.50
    tover
    -0.48
    śród
    -0.48
    POSITIVE LOGITS
    IntoConstraints
    0.63
    馃
    0.62
    GRANTED
    0.62
     useCallback
    0.60
     Leth
    0.60
     ').
    0.58
    SBATCH
    0.57
    TRIBUN
    0.57
     arşivlendi
    0.57
    ]='\
    0.57
    Act Density 0.009%

    No Known Activations