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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "on" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     by
    -0.15
    antas
    -0.14
    .platform
    -0.14
     Lup
    -0.14
    eder
    -0.14
    carbon
    -0.13
    at
    -0.13
    anas
    -0.13
     jur
    -0.13
    rax
    -0.13
    POSITIVE LOGITS
    emale
    0.19
    )((((
    0.18
    isko
    0.17
    essel
    0.16
    веÑģÑĤи
    0.15
    μμε
    0.15
    enthal
    0.15
    esti
    0.14
    thal
    0.14
     cus
    0.14
    Act Density 0.007%

    No Known Activations