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

    Neuronpedia

    INDEX
    Explanations

    phrases related to making statements or representations about facts

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

    Statements about what someone made

    np_acts-logits-general · gemini-2.0-flash

    make statements or representations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IsContent
    -0.95
    IUrlHelper
    -0.94
    :✨
    -0.73
    UserScript
    -0.73
     ProtoMessage
    -0.73
    NameInMap
    -0.72
    ReusableCell
    -0.71
    MLLoader
    -0.70
    CopyWith
    -0.69
    LookAnd
    -0.69
    POSITIVE LOGITS
     investments
    0.51
    ミング
    0.47
    assioned
    0.47
    sique
    0.47
    헌
    0.46
     investment
    0.46
    essive
    0.45
    ometrial
    0.44
    lawayo
    0.44
     những
    0.43
    Act Density 0.151%

    No Known Activations