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

    Neuronpedia

    INDEX
    Explanations

    phrases starting with "it's" followed by actions or qualities

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing a lack of clarity or confusion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     unmarked
    -0.64
     reception
    -0.63
     scattering
    -0.63
     Galile
    -0.62
    wagen
    -0.61
     whirlwind
    -0.60
     compiling
    -0.60
     friendly
    -0.60
     buggy
    -0.59
    agher
    -0.58
    POSITIVE LOGITS
    elong
    0.99
    ¹
    0.88
    erest
    0.87
    votes
    0.82
    requires
    0.82
    bet
    0.80
    tor
    0.78
    ¬
    0.78
    feat
    0.77
    prem
    0.75
    Act Density 0.554%

    No Known Activations