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

    Neuronpedia

    INDEX
    Explanations

    comparisons between strengths and weaknesses in performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rite
    -0.15
     hol
    -0.15
     linh
    -0.14
    swire
    -0.14
    anta
    -0.14
     Independence
    -0.14
    lick
    -0.14
    tember
    -0.14
    acl
    -0.14
    ustom
    -0.13
    POSITIVE LOGITS
    _controls
    0.17
     Controls
    0.16
     controls
    0.15
    çĴ
    0.15
    ammen
    0.15
    .controls
    0.15
     Symbol
    0.14
    Ïģιν
    0.14
    OOT
    0.14
    .dtd
    0.14
    Act Density 0.146%

    No Known Activations