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

    Neuronpedia

    INDEX
    Explanations

    phrases related to providing information or advice

    oai_token-act-pair · gpt-3.5-turbo

    phrases that address the reader directly, particularly those starting with "if you."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    "},
    -0.70
    ".[
    -0.66
    WIND
    -0.64
     replaced
    -0.63
    upon
    -0.62
    OTOS
    -0.60
    roxy
    -0.60
    ."[
    -0.59
    EVA
    -0.59
    Js
    -0.58
    POSITIVE LOGITS
     yourself
    1.18
     yourselves
    1.04
     your
    0.76
     Yourself
    0.76
    entary
    0.69
    >)
    0.64
     ANY
    0.64
     adventurous
    0.64
    audi
    0.63
     unlucky
    0.62
    Act Density 0.373%

    No Known Activations