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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "this" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rug
    -0.17
    rum
    -0.14
    geber
    -0.14
    oma
    -0.13
    å¥ı
    -0.13
    ubber
    -0.13
    ategor
    -0.13
    thal
    -0.13
    cox
    -0.13
     Cumberland
    -0.13
    POSITIVE LOGITS
     year
    0.21
     годÑĥ
    0.20
    eon
    0.17
     past
    0.16
    year
    0.16
    eldo
    0.15
    opic
    0.15
    .year
    0.15
     morning
    0.15
     Jahr
    0.15
    Act Density 0.044%

    No Known Activations