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

    Neuronpedia

    INDEX
    Explanations

    words related to updates or changes

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating updates or changes to information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rance
    -0.64
     itching
    -0.62
     pregnancies
    -0.61
    grain
    -0.61
    sbm
    -0.61
    reprene
    -0.60
    icipated
    -0.59
    ucl
    -0.58
     surveys
    -0.58
    SPONSORED
    -0.57
    POSITIVE LOGITS
     accommodate
    1.09
     reflect
    1.01
     conserve
    0.97
     avoid
    0.96
     minimize
    0.96
     maximize
    0.94
     eliminate
    0.93
     appease
    0.93
     resemble
    0.91
    ggles
    0.91
    Act Density 0.134%

    No Known Activations