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

    Neuronpedia

    INDEX
    Explanations

    commands or prompts starting with "Tell"

    oai_token-act-pair · gpt-3.5-turbo

    imperative prompts for sharing information or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ILCS
    -0.83
    perty
    -0.78
    erala
    -0.74
    à¤
    -0.68
    ãĤ§
    -0.66
    urdue
    -0.65
    ISH
    -0.65
    Merit
    -0.65
    cru
    -0.64
    cdn
    -0.62
    POSITIVE LOGITS
    tale
    1.37
    tell
    1.25
     Tell
    1.24
    ingly
    1.04
    iary
    0.91
    Tell
    0.90
    biz
    0.89
     me
    0.84
    ings
    0.83
     tell
    0.82
    Act Density 0.011%

    No Known Activations