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

    Neuronpedia

    INDEX
    Explanations

    references to safety and secure environments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    errupted
    -0.16
    ëŀij
    -0.15
    usk
    -0.14
    esis
    -0.13
     ÑĤака
    -0.13
    lando
    -0.13
    lide
    -0.13
    à¸ģร
    -0.13
    awaiter
    -0.13
     fewer
    -0.13
    POSITIVE LOGITS
    (er
    0.16
    ousel
    0.16
    ola
    0.15
    vest
    0.15
     deposit
    0.14
    ient
    0.14
    oux
    0.13
    /fast
    0.13
    azz
    0.13
     safe
    0.13
    Act Density 0.035%

    No Known Activations