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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating prior steps or actions that need to be taken before proceeding with a process or task

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

    Preceding actions or steps

    np_acts-logits-general · gemini-2.0-flash

    before doing something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     chi̍t
    -0.70
    Geplaatst
    -0.56
    SBATCH
    -0.52
    XmlEnum
    -0.48
     recevrez
    -0.48
    marvin
    -0.45
     ProtoMessage
    -0.45
    AddHtmlAttribute
    -0.43
    ///</
    -0.43
    BeginContext
    -0.43
    POSITIVE LOGITS
     any
    0.78
    expandindo
    0.70
    Enders
    0.70
     quelconque
    0.69
     Qualquer
    0.67
     cualquier
    0.67
    AutoresizingMask
    0.67
     Before
    0.66
     embarking
    0.66
     before
    0.66
    Act Density 0.088%

    No Known Activations