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

    Neuronpedia

    INDEX
    Explanations

    adjectives expressing certainty or inevitability

    oai_token-act-pair · gpt-3.5-turbo

    terms that convey certainty or strong affirmation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     trim
    -0.69
    lower
    -0.69
    ramid
    -0.67
    oa
    -0.66
    lder
    -0.65
    yers
    -0.65
     specific
    -0.64
    ctors
    -0.64
     fancy
    -0.64
    ria
    -0.63
    POSITIVE LOGITS
     undeniable
    2.21
     unstoppable
    2.13
     irresistible
    2.04
     unmist
    1.92
     irre
    1.85
     irreversible
    1.81
     irresist
    1.80
     inex
    1.80
     undeniably
    1.74
     unparalleled
    1.70
    Act Density 0.060%

    No Known Activations