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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating emphasis or importance

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the concept of truth or reality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itches
    -0.67
    iband
    -0.64
    hoe
    -0.64
    throp
    -0.62
    inges
    -0.62
    aturdays
    -0.61
     wills
    -0.61
    andise
    -0.60
    pled
    -0.60
     rites
    -0.59
    POSITIVE LOGITS
    cussion
    0.91
     not
    0.85
     NOT
    0.85
    olation
    0.81
     still
    0.76
     indeed
    0.76
     unclear
    0.75
     definitely
    0.75
     undoubtedly
    0.75
    ometric
    0.74
    Act Density 0.185%

    No Known Activations