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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the letter combination "Se" at the start of words or in certain contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ships
    -0.21
    ship
    -0.19
    so
    -0.19
    sh
    -0.19
    land
    -0.18
    riet
    -0.18
    ness
    -0.17
     zas
    -0.17
    rias
    -0.17
    soever
    -0.16
    POSITIVE LOGITS
    ITHER
    0.16
    eed
    0.16
    isko
    0.15
    infeld
    0.14
    idel
    0.14
    aside
    0.14
    URITY
    0.14
    оÑĢÑĭ
    0.14
    @nate
    0.14
    lected
    0.13
    Act Density 0.035%

    No Known Activations