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

    Neuronpedia

    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    past and present tense forms of the verb "to be."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bury
    -0.69
    ween
    -0.65
    Ghost
    -0.65
    uld
    -0.63
     Bat
    -0.63
    orce
    -0.63
    laughs
    -0.62
    ourt
    -0.62
    Wonder
    -0.61
    sburg
    -0.60
    POSITIVE LOGITS
     also
    1.02
     therefore
    0.98
     mainly
    0.86
     essentially
    0.86
     definitely
    0.84
     furthermore
    0.83
     basically
    0.83
     not
    0.81
     comprised
    0.81
     certainly
    0.80
    Act Density 0.461%

    No Known Activations