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

    Neuronpedia

    INDEX
    Explanations

    prompts indicating a desire for information or action

    oai_token-act-pair · gpt-3.5-turbo

    requests for information or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    è¦ļéĨĴ
    -0.87
    é¾
    -0.76
    displayText
    -0.72
    VEL
    -0.68
    SPONSORED
    -0.68
    åĤ
    -0.67
    externalActionCode
    -0.63
    士
    -0.62
     phyl
    -0.62
    ä¹ĭ
    -0.61
    POSITIVE LOGITS
     Want
    0.90
    Want
    0.78
    ickets
    0.76
    herty
    0.74
    atoon
    0.73
     Us
    0.71
    imus
    0.71
    leck
    0.71
    nels
    0.69
    gotten
    0.69
    Act Density 0.015%

    No Known Activations