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

    Neuronpedia

    INDEX
    Explanations

    complex phrases related to academic or professional contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to students and educational contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Samar
    -0.70
     prol
    -0.70
    é¾įå¥ij士
    -0.70
     Golem
    -0.67
     publicity
    -0.66
     Negro
    -0.65
     gloom
    -0.64
     snail
    -0.63
     cart
    -0.62
     buggy
    -0.62
    POSITIVE LOGITS
    selves
    0.95
    acca
    0.88
    hip
    0.88
    agree
    0.85
    ¹
    0.85
    overe
    0.80
    administ
    0.80
    bryce
    0.79
    their
    0.78
    £
    0.76
    Act Density 0.256%

    No Known Activations