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

    Neuronpedia

    INDEX
    Explanations

    phrases relating to the act of communicating ideas or information

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "tell."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    engeance
    -0.75
    rane
    -0.72
    urdue
    -0.71
    cdn
    -0.71
    ilings
    -0.66
    iazep
    -0.66
    amic
    -0.65
    scill
    -0.65
    ded
    -0.64
    hered
    -0.64
    POSITIVE LOGITS
    tale
    1.39
    tell
    1.11
    ingly
    1.09
     Tell
    0.97
     tell
    0.97
    biz
    0.88
    Tell
    0.79
    soType
    0.76
     tells
    0.76
     telling
    0.75
    Act Density 0.044%

    No Known Activations