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

    Neuronpedia

    INDEX
    Explanations

    the word "Tell" in sentences as cues for actions or requests

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    imposed
    -0.71
    zinski
    -0.65
    urdue
    -0.64
    cells
    -0.61
    ccording
    -0.60
    berus
    -0.60
     ILCS
    -0.59
    isk
    -0.59
    adesh
    -0.59
     sidx
    -0.59
    POSITIVE LOGITS
    tale
    1.55
    ingly
    1.05
     us
    1.02
     tale
    0.90
     tales
    0.89
     me
    0.86
     stories
    0.81
     Tale
    0.80
     lies
    0.78
    tell
    0.77
    Act Density 0.049%

    No Known Activations