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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions or decisions with significant consequences

    oai_token-act-pair · gpt-3.5-turbo

    topics related to legal and social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Samar
    -0.63
    guyen
    -0.54
     deprecated
    -0.53
    ucket
    -0.53
    umbnails
    -0.52
    xtap
    -0.51
    quart
    -0.50
    BuyableInstoreAndOnline
    -0.49
     shoulders
    -0.49
     acron
    -0.49
    POSITIVE LOGITS
    ãĢĤ
    0.80
    )).
    0.76
    .''.
    0.73
     ASAP
    0.71
    .$
    0.69
     elsewhere
    0.69
     someday
    0.68
     safely
    0.66
    .</
    0.66
     whilst
    0.66
    Act Density 1.141%

    No Known Activations