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

    Neuronpedia

    INDEX
    Explanations

    special characters (&) along with words following them, possibly in a list or sequence

    oai_token-act-pair · gpt-3.5-turbo

    sentences or phrases that include the ampersand symbol '&'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atche
    -0.83
    ionage
    -0.79
    isoft
    -0.78
    etheless
    -0.78
    senal
    -0.75
     misunder
    -0.75
     Leilan
    -0.72
    enza
    -0.69
    owicz
    -0.69
    iguous
    -0.67
    POSITIVE LOGITS
    #$
    0.88
    optional
    0.83
    GAN
    0.81
    ^^^^
    0.79
    ++++++++++++++++
    0.76
    vine
    0.72
    etc
    0.69
    nect
    0.68
     Friends
    0.65
    ^^
    0.64
    Act Density 0.028%

    No Known Activations