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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the absence or lack of information or details

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the absence or lack of information or records

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     passages
    -0.61
    arms
    -0.60
    redients
    -0.59
    ggles
    -0.59
    ortment
    -0.58
    igl
    -0.56
     LOT
    -0.56
    itton
    -0.55
     gist
    -0.55
    little
    -0.55
    POSITIVE LOGITS
     anymore
    1.61
     nor
    1.42
     anywhere
    1.05
     whatsoever
    1.03
     necessarily
    1.03
     until
    0.90
    yet
    0.89
     any
    0.88
     unless
    0.88
     till
    0.86
    Act Density 0.214%

    No Known Activations