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

    Neuronpedia

    INDEX
    Explanations

    phrases related to establishing norms, guidelines, or standards

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

    "set" and its variations

    np_acts-logits-general · gemini-2.0-flash

    setting out precedents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    contentLoaded
    -0.78
    }{*}{}
    -0.66
    InputChange
    -0.59
     mouseClicked
    -0.58
    ULATION
    -0.58
     Additions
    -0.57
     :,
    -0.57
    UseVisualStyle
    -0.57
    lossenen
    -0.57
    ########.
    -0.55
    POSITIVE LOGITS
     aside
    0.81
     forth
    0.70
     Setting
    0.66
     setting
    0.65
     SETTING
    0.65
    Setting
    0.64
     Setter
    0.61
     set
    0.61
     setter
    0.59
     precedents
    0.59
    Act Density 0.073%

    No Known Activations