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

    Neuronpedia

    INDEX
    Explanations

    keywords related to safety and security

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onAttach
    -0.84
    WithIOException
    -0.77
    Посилання
    -0.76
    GetMapping
    -0.75
     Abp
    -0.73
    Kontrola
    -0.72
    upol
    -0.71
    ANNES
    -0.71
     Gazetteer
    -0.71
    @[+][
    -0.70
    POSITIVE LOGITS
     safe
    3.40
     Safe
    3.12
    safe
    2.98
    Safe
    2.93
     SAFE
    2.81
    SAFE
    2.62
     safer
    2.26
     safely
    2.19
     safest
    2.13
    saf
    1.89
    Act Density 0.070%

    No Known Activations