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

    Neuronpedia

    INDEX
    Explanations

    sentences that start with a statement or include the word "statement"

    oai_token-act-pair · gpt-3.5-turbo

    official statements from organizations or authorities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    grade
    -0.65
     sneaking
    -0.63
    hoe
    -0.63
     outdoors
    -0.62
    liest
    -0.62
     eyed
    -0.61
     glimps
    -0.61
    wat
    -0.60
     penetration
    -0.59
    worm
    -0.59
    POSITIVE LOGITS
    Statement
    0.90
     apologizing
    0.81
     spokesperson
    0.78
     Regarding
    0.78
     apology
    0.77
     behalf
    0.76
     respons
    0.71
     thanking
    0.71
     responding
    0.71
     apolog
    0.70
    Act Density 0.291%

    No Known Activations