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

    Neuronpedia

    INDEX
    Explanations

    locations or places

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating actions or statuses involving people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     SB
    -0.70
     Crimson
    -0.68
     Hacker
    -0.67
    ¶ħ
    -0.62
     Sakuya
    -0.61
     Briggs
    -0.59
     Features
    -0.59
     Prompt
    -0.58
     Tun
    -0.58
     Cthulhu
    -0.58
    POSITIVE LOGITS
    Interstitial
    0.84
    imum
    0.80
    ilater
    0.74
     congreg
    0.74
     reside
    0.73
    ezvous
    0.72
     intersect
    0.71
    REF
    0.67
     resides
    0.64
    VICE
    0.64
    Act Density 0.366%

    No Known Activations