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

    Neuronpedia

    INDEX
    Explanations

    phrases related to verification and confirmation processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <eos>
    -0.51
    ↵↵
    -0.44
     
    -0.41
     non
    -0.37
    next
    -0.35
     single
    -0.35
     "
    -0.34
    .
    -0.33
     so
    -0.33
     pers
    -0.33
    POSITIVE LOGITS
     Majefty
    1.19
     CreateTagHelper
    1.18
     nahilalakip
    1.17
     ſtate
    1.15
     myſelf
    1.15
     Efq
    1.14
     itſelf
    1.12
    AsUp
    1.11
     pleaſure
    1.10
    ſelves
    1.10
    Act Density 0.026%

    No Known Activations