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

    Neuronpedia

    INDEX
    Explanations

    verbs related to decision-making and consequences

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to significant consequences or critical situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Malays
    -0.74
     Malaysia
    -0.57
     Malaysian
    -0.54
     Lumpur
    -0.54
    Shar
    -0.53
     coincides
    -0.52
    photos
    -0.52
     Lion
    -0.52
     Haf
    -0.50
     Symb
    -0.50
    POSITIVE LOGITS
    pmwiki
    0.66
    ãĥĩãĤ£
    0.64
     nonetheless
    0.63
    etheless
    0.61
     nevertheless
    0.57
    untarily
    0.56
    ptin
    0.55
    ãĤ´
    0.55
    ãĤ¦ãĤ¹
    0.55
    âĵĺ
    0.54
    Act Density 1.652%

    No Known Activations