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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "leave" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    akh
    -0.15
    alat
    -0.15
    yo
    -0.15
    /from
    -0.15
    276
    -0.14
    ORK
    -0.14
     dus
    -0.14
    712
    -0.14
    atsu
    -0.14
     Preference
    -0.14
    POSITIVE LOGITS
     behind
    0.21
     khá»ıi
    0.18
    -handed
    0.17
    roke
    0.17
     town
    0.17
     aside
    0.17
    алÑĥ
    0.16
    æk
    0.16
    vard
    0.16
    enant
    0.16
    Act Density 0.035%

    No Known Activations