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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing telling or narrating a story

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "tell" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urdue
    -0.76
    zinski
    -0.72
     ILCS
    -0.71
    lik
    -0.67
    imposed
    -0.67
    JV
    -0.66
    rane
    -0.66
    EEE
    -0.65
    cdn
    -0.64
    nam
    -0.63
    POSITIVE LOGITS
    tale
    1.47
    ingly
    1.11
     tales
    0.84
    tell
    0.83
     us
    0.82
     tale
    0.80
     me
    0.72
     Prompt
    0.71
    llor
    0.71
    ously
    0.71
    Act Density 0.050%

    No Known Activations