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

    Neuronpedia

    INDEX
    Explanations

    direct speech indicating communication of an event or information

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "told."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ILCS
    -0.77
    icons
    -0.73
    adesh
    -0.70
    engeance
    -0.68
    abilities
    -0.67
    ilings
    -0.64
    pite
    -0.64
    posure
    -0.64
    reci
    -0.64
    otion
    -0.64
    POSITIVE LOGITS
    tale
    1.14
    tell
    0.95
     Tell
    0.81
    warn
    0.76
    told
    0.76
     tells
    0.75
     bluntly
    0.74
    ingly
    0.74
     told
    0.74
     BuzzFeed
    0.73
    Act Density 0.059%

    No Known Activations