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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating someone's preferences or desires

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "I don't want to" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soDeliveryDate
    -0.88
     Enhancement
    -0.69
    ccording
    -0.68
     Needs
    -0.65
    footed
    -0.64
    figured
    -0.63
    adder
    -0.62
     Compass
    -0.62
     reperto
    -0.62
    gradient
    -0.61
    POSITIVE LOGITS
     anymore
    1.44
     nor
    1.09
     anywhere
    1.03
     necessarily
    1.03
     bother
    1.02
     whatsoever
    0.93
     anybody
    0.93
     any
    0.92
     anything
    0.91
     mention
    0.87
    Act Density 0.190%

    No Known Activations