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

    Neuronpedia

    INDEX
    Explanations

    common verbs used in instructions or explanations

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "there are."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    matter
    -0.83
    iliation
    -0.71
    ename
    -0.71
    isition
    -0.70
    speak
    -0.70
    dom
    -0.69
    analysis
    -0.67
    ileaks
    -0.66
    aired
    -0.66
    Initialized
    -0.65
    POSITIVE LOGITS
     plenty
    1.20
     lots
    1.08
     exceptions
    1.07
     indications
    1.04
     many
    1.04
     countless
    1.03
     several
    1.02
     few
    1.01
     similarities
    0.97
     dozens
    0.97
    Act Density 0.092%

    No Known Activations