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

    Neuronpedia

    INDEX
    Explanations

    phrases that refer to groups or collections of items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    styleUrls
    -0.44
    pragma
    -0.41
     <<<<<<<<<<<<<<
    -0.41
    php
    -0.39
    <code>
    -0.39
    {"
    -0.39
     gern
    -0.38
    Transkript
    -0.36
     effectively
    -0.35
    /**
    -0.35
    POSITIVE LOGITS
     ProtoMessage
    0.73
    ftagPool
    0.69
     toss
    0.68
     незавершена
    0.66
     amizade
    0.65
     tossed
    0.65
     avoient
    0.64
     sit
    0.63
     shaped
    0.62
     tossing
    0.62
    Act Density 0.341%

    No Known Activations