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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "are."

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

    describing 'they are' status

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hsl
    -0.36
    prefixer
    -0.36
    BCF
    -0.35
    dziew
    -0.35
    rtf
    -0.35
    jshint
    -0.34
    ostante
    -0.34
    Sø
    -0.33
     casque
    -0.33
    Pug
    -0.33
    POSITIVE LOGITS
     are
    0.96
     blevet
    0.85
     blitt
    0.82
    are
    0.77
     бъдат
    0.76
     estão
    0.73
     is
    0.71
     Administrativna
    0.71
     입니다
    0.71
     sont
    0.70
    Act Density 0.011%

    No Known Activations