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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a small amount or degree of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ed
    -0.19
    ftware
    -0.17
    nt
    -0.16
    hi
    -0.15
     somewhat
    -0.15
    hs
    -0.15
    leo
    -0.14
    δί
    -0.14
    hiro
    -0.14
    ho
    -0.14
    POSITIVE LOGITS
    umen
    0.29
    /stdc
    0.26
    .ly
    0.26
    mapped
    0.25
    Torrent
    0.21
    umin
    0.20
    rary
    0.19
    tern
    0.18
     more
    0.18
     bit
    0.18
    Act Density 0.019%

    No Known Activations