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

    Neuronpedia

    INDEX
    Explanations

    the word "as" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    introducing examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Conſ
    -0.59
     Reſ
    -0.54
     Anſ
    -0.53
     laſt
    -0.52
     jsPsych
    -0.52
     itſelf
    -0.50
     purpoſe
    -0.48
    !*\
    -0.47
     Inſ
    -0.47
     juſ
    -0.47
    POSITIVE LOGITS
    גון
    0.63
    เช่น
    0.63
     såsom
    0.62
     like
    0.61
    如
    0.59
     zoals
    0.56
     whereas
    0.56
     имеются
    0.55
     LIKE
    0.54
    んや
    0.54
    Act Density 0.028%

    No Known Activations