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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "everything" and related expressions indicating totality or completeness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     certain
    -0.53
     several
    -0.51
     banyak
    -0.50
     many
    -0.49
     certaines
    -0.47
     beberapa
    -0.47
     some
    -0.45
     daž
    -0.45
    複数
    -0.45
     certaine
    -0.44
    POSITIVE LOGITS
     including
    0.99
    Including
    0.97
    including
    0.97
     Including
    0.95
     imaginable
    0.89
     INCLUDING
    0.84
    INCLUDING
    0.82
     incluyendo
    0.82
     včetně
    0.79
     revolves
    0.79
    Act Density 0.161%

    No Known Activations