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

    Neuronpedia

    INDEX
    Explanations

    the verb "to be" in various forms and negations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erker
    -0.54
     $_(
    -0.49
    __*/
    -0.48
    riwal
    -0.47
    amoan
    -0.47
    principalTable
    -0.45
    []>(
    -0.45
    الحياه
    -0.45
    Predecesor
    -0.44
     volontà
    -0.43
    POSITIVE LOGITS
     necessarily
    0.59
    necessarily
    0.56
     anymore
    0.54
     anybody
    0.53
    <bos>
    0.48
     exactly
    0.48
     anything
    0.47
     anywhere
    0.46
    ’
    0.46
     anyone
    0.44
    Act Density 0.132%

    No Known Activations