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

    Neuronpedia

    INDEX
    Explanations

    terms related to established and verified effectiveness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     impl
    -0.15
     shall
    -0.15
    endi
    -0.14
    ular
    -0.14
    gram
    -0.14
    ernen
    -0.14
    289
    -0.14
    orp
    -0.14
    orf
    -0.14
     Nap
    -0.13
    POSITIVE LOGITS
    TRL
    0.16
    -existing
    0.15
    ellt
    0.15
    dü
    0.15
    eve
    0.15
    essenger
    0.14
    DAY
    0.14
    çĸĨ
    0.14
    едÑĮ
    0.14
    -src
    0.14
    Act Density 0.014%

    No Known Activations