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

    Neuronpedia

    INDEX
    Explanations

    phrases associated with the concept of addition or accumulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dil
    -0.18
    qli
    -0.16
     dil
    -0.16
    :↵↵↵↵↵↵
    -0.15
    гÑĢад
    -0.15
    stants
    -0.14
     tslib
    -0.14
    VRT
    -0.14
    ibraries
    -0.14
     gravid
    -0.14
    POSITIVE LOGITS
    iah
    0.19
    ti
    0.16
    TA
    0.16
    Č↵
    0.15
    ợ
    0.14
    agit
    0.14
    ipc
    0.14
    butt
    0.14
    razier
    0.14
    prec
    0.14
    Act Density 0.006%

    No Known Activations