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

    Neuronpedia

    INDEX
    Explanations

    phrases related to taking something away or removing something from a situation

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "take away."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ipel
    -0.79
    bia
    -0.72
    mop
    -0.69
    ouf
    -0.69
    anwhile
    -0.69
    enegger
    -0.68
    urgy
    -0.66
    bis
    -0.65
    pas
    -0.65
    anners
    -0.64
    POSITIVE LOGITS
     cart
    0.77
     away
    0.76
     Territories
    0.74
     discretion
    0.68
     spo
    0.65
     AW
    0.63
     EVs
    0.61
     from
    0.61
     arbitrarily
    0.60
     tablets
    0.59
    Act Density 0.015%

    No Known Activations