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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "told."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "told" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ILCS
    -0.75
    adesh
    -0.75
    imates
    -0.71
    racted
    -0.70
    posure
    -0.68
    untled
    -0.66
    ingu
    -0.66
    ateurs
    -0.66
    Naz
    -0.66
    governmental
    -0.65
    POSITIVE LOGITS
    tale
    1.32
     him
    0.91
     us
    0.90
     me
    0.89
    ingly
    0.87
     tales
    0.75
     them
    0.74
    wered
    0.73
    tell
    0.72
     stories
    0.72
    Act Density 0.066%

    No Known Activations