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

    Neuronpedia

    INDEX
    Explanations

    the name "Ak" followed by various other characters

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Ak" across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enegger
    -0.77
    iculty
    -0.72
    åĤ
    -0.69
     Reaper
    -0.69
     Quadro
    -0.67
     Hurricanes
    -0.66
    sburgh
    -0.65
     Scotia
    -0.65
    FORMATION
    -0.64
    ACTED
    -0.64
    POSITIVE LOGITS
    atsuki
    1.08
    ule
    0.99
    ansas
    0.98
    umar
    0.96
    uri
    0.96
    uin
    0.95
    htar
    0.93
    rue
    0.93
    adem
    0.92
    ura
    0.90
    Act Density 0.012%

    No Known Activations