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

    Neuronpedia

    INDEX
    Explanations

    phrases that introduce or relate to examples

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    readcr
    -0.18
    azer
    -0.17
    ACE
    -0.15
    WithContext
    -0.15
    ê
    -0.15
    ì¢Į
    -0.14
    ÏĢα
    -0.14
    ROP
    -0.14
    ieren
    -0.14
    alendar
    -0.14
    POSITIVE LOGITS
     us
    0.19
    like
    0.19
     such
    0.18
    such
    0.18
    .a
    0.16
     ours
    0.16
    å¦Ĥ
    0.16
    s
    0.15
    wie
    0.14
     ass
    0.14
    Act Density 0.022%

    No Known Activations