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

    Neuronpedia

    INDEX
    Explanations

    present tense forms of the verb "to be."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Theſe
    -0.74
    +#+#
    -0.71
     ſame
    -0.67
    StatusOK
    -0.67
    foundland
    -0.66
    ſelf
    -0.66
     Sima
    -0.64
     vertes
    -0.64
     inferiority
    -0.63
    ]--;
    -0.63
    POSITIVE LOGITS
     there
    1.00
    there
    0.76
     There
    0.75
     theres
    0.70
    There
    0.68
    theres
    0.65
    Theres
    0.65
     terdapat
    0.65
     هناك
    0.63
     existe
    0.63
    Act Density 0.123%

    No Known Activations