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

    Neuronpedia

    INDEX
    Explanations

    past tense verbs indicating actions taken or changes made

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     addCriterion
    -0.18
    caa
    -0.16
    $LANG
    -0.15
    andas
    -0.15
    wil
    -0.14
    ï¼ģï¼ģ↵↵
    -0.14
     Ahead
    -0.14
    lâm
    -0.14
    eri
    -0.14
    ادة
    -0.14
    POSITIVE LOGITS
    -over
    0.20
     fourth
    0.19
    -back
    0.18
    -about
    0.18
    -off
    0.18
    :async
    0.18
    -up
    0.17
    -to
    0.16
    -for
    0.16
    own
    0.16
    Act Density 0.088%

    No Known Activations