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

    Neuronpedia

    INDEX
    Explanations

    phrases related to online content or marketing, with a focus on preparing for a specific topic or event

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and special characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quart
    -0.71
    âĢij
    -0.68
    atlantic
    -0.65
     mir
    -0.64
    ±
    -0.63
     greenhouse
    -0.62
    rael
    -0.61
    form
    -0.61
    born
    -0.60
    parser
    -0.59
    POSITIVE LOGITS
     Lastly
    1.13
     Finally
    1.09
     Same
    1.02
     Whenever
    1.02
     Another
    1.00
     Exactly
    0.98
     Though
    0.98
     Whoever
    0.98
     Usually
    0.97
     Despite
    0.97
    Act Density 0.262%

    No Known Activations