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

    Neuronpedia

    INDEX
    Explanations

    phrases related to upcoming events or scheduled appearances

    oai_token-act-pair · gpt-3.5-turbo

    the verb "be" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Oops
    -0.74
     comprehension
    -0.68
    rehens
    -0.65
     assurance
    -0.64
    emonic
    -0.64
     theorem
    -0.64
    76561
    -0.63
    arta
    -0.63
     promise
    -0.63
     imagination
    -0.63
    POSITIVE LOGITS
     able
    0.94
    ige
    0.94
    heading
    0.93
     replaced
    0.90
     joining
    0.85
    AMS
    0.82
     rewarded
    0.82
     honored
    0.82
     featured
    0.82
     honoured
    0.78
    Act Density 0.130%

    No Known Activations