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

    Neuronpedia

    INDEX
    Explanations

    phrases that include verbs of actions or states

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "known" often paired with an infinitive verb

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    earable
    -0.69
     sponsored
    -0.68
     Mehran
    -0.68
     jackets
    -0.66
     proposals
    -0.65
     coats
    -0.64
     Donation
    -0.64
     exams
    -0.63
    case
    -0.62
     scholarships
    -0.61
    POSITIVE LOGITS
    \">
    0.87
    YS
    0.78
    »Ĵ
    0.77
    cot
    0.76
    DOM
    0.75
    soType
    0.73
    ogle
    0.71
    Override
    0.70
    lie
    0.70
    ":"","
    0.70
    Act Density 0.086%

    No Known Activations