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

    Neuronpedia

    INDEX
    Explanations

    text related to tables of contents and structured document formats

    oai_token-act-pair · gpt-3.5-turbo

    references to content and organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tremend
    -0.66
    gpu
    -0.60
     whale
    -0.59
    WAY
    -0.58
    ahime
    -0.57
    arent
    -0.56
    ppard
    -0.54
     Pradesh
    -0.53
     natural
    -0.53
    agara
    -0.52
    POSITIVE LOGITS
     Scrib
    0.63
    çļ
    0.61
    auder
    0.60
     hier
    0.55
     pus
    0.55
     Circus
    0.54
     Copy
    0.52
     pots
    0.52
    sels
    0.52
    GUI
    0.52
    Act Density 1.279%

    No Known Activations