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

    Neuronpedia

    INDEX
    Explanations

    phrases related to consuming or filling gaps or voids, especially related to physical objects or resources

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to quantities and their management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     boycot
    -0.73
    swer
    -0.70
     warr
    -0.69
    SPONSORED
    -0.69
     WATCH
    -0.65
    KO
    -0.65
    cision
    -0.64
    mbuds
    -0.63
    VIEW
    -0.63
    chart
    -0.61
    POSITIVE LOGITS
     leftover
    1.05
     bits
    0.94
     chunks
    0.93
     scraps
    0.92
     excess
    0.88
     remnants
    0.86
     toxins
    0.84
    berries
    0.83
     discarded
    0.79
     nutrients
    0.79
    Act Density 0.530%

    No Known Activations