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

    Neuronpedia

    INDEX
    Explanations

    phrases related to technology and humanity

    oai_token-act-pair · gpt-3.5-turbo

    discussions related to human impact on technology and the environment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    é¾įå¥ij士
    -0.77
    leck
    -0.68
    Roll
    -0.68
    ricular
    -0.65
     Refresh
    -0.65
    oother
    -0.64
    risome
    -0.63
    alos
    -0.60
     Rican
    -0.60
    icion
    -0.60
    POSITIVE LOGITS
    aviour
    0.76
    aeda
    0.73
    atures
    0.71
     Sanct
    0.64
     extinct
    0.64
     primates
    0.63
    enko
    0.62
    ande
    0.62
     instinct
    0.62
    interest
    0.62
    Act Density 0.118%

    No Known Activations