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

    Neuronpedia

    INDEX
    Explanations

    phrases related to safety and risk factors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Followed by prepositions

    np_acts-logits-general · gemini-2.0-flash

    this item's function or action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Lähteet
    -0.82
    KommentareTeilen
    -0.65
     ujednoznacz
    -0.64
    FDRE
    -0.62
    #+#
    -0.62
    verwijspagina
    -0.59
    ContentAlignment
    -0.59
     PeEnEo
    -0.58
     linkovi
    -0.58
    BeginInit
    -0.56
    POSITIVE LOGITS
    该
    0.70
    这部
    0.68
    这款
    0.65
    該
    0.62
    这只
    0.60
     该
    0.60
     machine
    0.59
    这座
    0.57
    本作
    0.56
     nó
    0.56
    Act Density 1.046%

    No Known Activations