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

    Neuronpedia

    INDEX
    Explanations

    website URLs

    oai_token-act-pair · gpt-3.5-turbo

    specific identifiers or references in a structured format, such as dates or URLs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    terday
    -0.79
    aturday
    -0.72
    ometime
    -0.71
    nce
    -0.67
    esides
    -0.66
    roximately
    -0.63
    =-=-
    -0.61
    umerous
    -0.59
     secondly
    -0.59
    ursday
    -0.58
    POSITIVE LOGITS
     spy
    0.52
     doping
    0.50
     sorcery
    0.49
     graft
    0.49
     Photoshop
    0.46
     wizard
    0.46
     plagiar
    0.46
     pir
    0.45
     psychic
    0.45
     Sherlock
    0.45
    Act Density 1.158%

    No Known Activations