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

    Neuronpedia

    INDEX
    Explanations

    phrases related to a requirement, necessity, or obligation

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating relationships or connections between concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reviewer
    -0.72
     Onion
    -0.63
     eyeing
    -0.63
     pressing
    -0.57
    mort
    -0.57
     rash
    -0.56
     mir
    -0.56
    ahime
    -0.55
     prest
    -0.55
    SHIP
    -0.54
    POSITIVE LOGITS
    wered
    1.03
     happen
    1.02
     be
    1.01
     occur
    0.99
     suffice
    0.97
     belong
    0.90
     originate
    0.89
     involve
    0.87
     preced
    0.85
     exist
    0.83
    Act Density 0.068%

    No Known Activations