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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "for"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utters
    -0.16
    esser
    -0.14
    ίγ
    -0.14
    ãĥĥãĥĦ
    -0.14
     everlasting
    -0.13
    Å¡ek
    -0.13
    {:
    -0.13
    ữ
    -0.13
    asan
    -0.13
    rias
    -0.13
    POSITIVE LOGITS
    orp
    0.16
    bidden
    0.15
    ç¼
    0.15
    kses
    0.15
    agan
    0.14
    peria
    0.14
    bilt
    0.14
    εÏĦ
    0.14
    920
    0.13
    erset
    0.13
    Act Density 0.017%

    No Known Activations