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

    Neuronpedia

    INDEX
    Explanations

    instances where the phrase "No more" is mentioned

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the concept of "more" or the lack thereof

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ahime
    -0.72
    lyak
    -0.66
    itton
    -0.63
    gypt
    -0.63
     chains
    -0.62
    ili
    -0.62
    Wi
    -0.59
     Lum
    -0.58
    rane
    -0.57
    andals
    -0.56
    POSITIVE LOGITS
     whatsoever
    1.47
     nor
    1.09
     anymore
    0.87
    ody
    0.76
     anywhere
    0.75
     dime
    0.73
    EMBER
    0.72
     except
    0.71
    mega
    0.71
    brainer
    0.67
    Act Density 0.123%

    No Known Activations