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

    Neuronpedia

    INDEX
    Explanations

    text that contains numerical values or references to quantity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    󠁿
    -0.79
     itſelf
    -0.78
    }{*}{}
    -0.77
     myſelf
    -0.76
     uſed
    -0.76
     Efq
    -0.74
    — 
    -0.73
     MongoClient
    -0.72
    ^(@)
    -0.71
    }$_
    -0.71
    POSITIVE LOGITS
    <eos>
    0.54
    .
    0.51
    ↵
    0.47
    жев
    0.46
    edit
    0.45
    SF
    0.45
    ...
    0.45
    #
    0.44
    blog
    0.44
     #
    0.44
    Act Density 0.123%

    No Known Activations