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

    Neuronpedia

    INDEX
    Explanations

    phone numbers

    oai_token-act-pair · gpt-3.5-turbo

    numeric values related to contact information or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hare
    -0.80
    iners
    -0.67
    lest
    -0.63
     plur
    -0.62
    ccording
    -0.62
    phies
    -0.59
    resh
    -0.59
     passionate
    -0.58
     bark
    -0.57
     neglected
    -0.57
    POSITIVE LOGITS
     Collider
    0.70
     Detention
    0.69
    ;;;;;;;;;;;;
    0.68
     [*]
    0.68
     Facility
    0.66
     CrossRef
    0.66
     DOI
    0.66
     IMAGES
    0.66
     UDP
    0.64
     Magicka
    0.63
    Act Density 0.062%

    No Known Activations