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

    Neuronpedia

    INDEX
    Explanations

    references to existence or presence

    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
    -0.78
    speak
    -0.75
    ileaks
    -0.72
    ename
    -0.72
    rouse
    -0.72
    dom
    -0.69
    cation
    -0.68
    icut
    -0.68
    isition
    -0.68
    aired
    -0.67
    POSITIVE LOGITS
     plenty
    1.15
     exceptions
    1.05
     lots
    1.00
     indications
    0.97
     no
    0.95
     similarities
    0.94
     occasions
    0.90
     fewer
    0.89
     tons
    0.87
     parallels
    0.86
    Act Density 0.084%

    No Known Activations