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

    Neuronpedia

    INDEX
    Explanations

    phrases mentioning the concept of 'conclusion' or 'finality'

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "last" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gregation
    -0.64
    quartered
    -0.63
    xual
    -0.62
     Parsons
    -0.61
    renheit
    -0.60
    orsi
    -0.59
    RN
    -0.58
    ometimes
    -0.57
    pherd
    -0.56
     Lam
    -0.55
    POSITIVE LOGITS
     ditch
    0.87
    ICA
    0.75
    istically
    0.75
     installment
    0.69
     gasp
    0.68
     glance
    0.66
     hurdle
    0.66
    irus
    0.66
     rites
    0.63
     avail
    0.62
    Act Density 0.025%

    No Known Activations