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

    Neuronpedia

    INDEX
    Explanations

    verbs related to performing actions

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and phrases indicating conditions or alternatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lass
    -0.71
    sted
    -0.65
    apsed
    -0.64
    Ö¼
    -0.63
    payer
    -0.63
     Hopkins
    -0.63
    lucent
    -0.60
    rained
    -0.60
    lex
    -0.58
     Believe
    -0.58
    POSITIVE LOGITS
     amusement
    1.10
     souven
    1.00
     purposes
    0.98
     entertainment
    0.90
     decoration
    0.90
     aiding
    0.84
     assisting
    0.84
     enjoyment
    0.81
     emergencies
    0.79
     gratification
    0.78
    Act Density 0.420%

    No Known Activations