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

    Neuronpedia

    INDEX
    Explanations

    phrases related to writing off or dismissing something

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the act of writing something off or dismissing it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aternity
    -0.75
    cius
    -0.75
    hig
    -0.73
    rador
    -0.73
    leground
    -0.68
    iosity
    -0.67
    ushi
    -0.65
    rouse
    -0.64
    gpu
    -0.64
    taboola
    -0.63
    POSITIVE LOGITS
    antha
    0.70
     scraps
    0.69
     waivers
    0.63
    RR
    0.62
     Ness
    0.60
     existence
    0.60
    umber
    0.59
    SI
    0.58
     Tup
    0.58
    umbered
    0.58
    Act Density 0.088%

    No Known Activations