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

    Neuronpedia

    INDEX
    Explanations

    phrases related to observation and commentary

    oai_token-act-pair · gpt-3.5-turbo

    phrases and expressions related to personal perception and experience

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    surprisingly
    -0.74
     ®
    -0.71
    etheless
    -0.69
    osponsors
    -0.62
    arist
    -0.61
    utterstock
    -0.58
    ensis
    -0.58
     "...
    -0.57
     purportedly
    -0.57
    collect
    -0.56
    POSITIVE LOGITS
    )."
    1.10
    .")
    1.08
    .'"
    1.01
    .""
    0.93
    ."
    0.92
    !'"
    0.91
     âĢ¦"
    0.91
    !"
    0.87
    '."
    0.86
    )"
    0.82
    Act Density 1.119%

    No Known Activations