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

    Neuronpedia

    INDEX
    Explanations

    references to "bit" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ed
    -0.23
    hall
    -0.19
    hots
    -0.17
    anine
    -0.16
    erver
    -0.16
    hist
    -0.15
    hs
    -0.15
    hound
    -0.15
    ists
    -0.15
    undry
    -0.15
    POSITIVE LOGITS
    umen
    0.33
    umin
    0.33
    /stdc
    0.32
    .ly
    0.28
    mapped
    0.25
    bucket
    0.24
    Torrent
    0.23
    angent
    0.23
    chez
    0.21
    tery
    0.19
    Act Density 0.011%

    No Known Activations