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

    Neuronpedia

    INDEX
    Explanations

    features related to language learning programs and their effectiveness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ift
    -0.17
    ifting
    -0.16
    710
    -0.14
    asso
    -0.14
     subrange
    -0.14
     Dunn
    -0.13
    ":[{↵
    -0.13
    ÑĢап
    -0.13
     lease
    -0.13
     matt
    -0.13
    POSITIVE LOGITS
    zo
    0.15
    THON
    0.15
     yat
    0.15
    ZO
    0.14
    .LookAndFeel
    0.14
    ANGER
    0.14
     ayn
    0.14
    bole
    0.14
    CATEGORY
    0.13
    REET
    0.13
    Act Density 0.155%

    No Known Activations