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

    Neuronpedia

    INDEX
    Explanations

    names of publishing companies and related phrases

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of company names and branding elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.70
    afety
    -0.63
    ournals
    -0.58
    ploy
    -0.56
    earcher
    -0.54
    itially
    -0.54
     fid
    -0.54
    ornia
    -0.54
    ourses
    -0.53
    issance
    -0.53
    POSITIVE LOGITS
    achev
    0.59
     Hai
    0.55
    ãĤ©
    0.55
    Ultra
    0.54
     Moonlight
    0.52
     Loki
    0.52
    âĦ¢
    0.52
    yahoo
    0.52
     Minion
    0.51
    xxxxxxxx
    0.51
    Act Density 1.374%

    No Known Activations