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

    Neuronpedia

    INDEX
    Explanations

    the word "instead" and its variations, indicating a focus on alternatives or substitutions

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

    "Instead of"

    np_acts-logits-general · gemini-2.0-flash

    instead of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.82
     επίσης
    -0.73
    modelBuilder
    -0.71
    AxisAlignment
    -0.64
    initComponents
    -0.62
     hlavně
    -0.61
    exitRule
    -0.61
     houſe
    -0.61
     intercession
    -0.61
     greateſt
    -0.61
    POSITIVE LOGITS
     than
    0.72
    帖最后由
    0.72
     findById
    0.58
     focus
    0.55
     focusing
    0.55
    ertale
    0.54
    :+:
    0.53
     opting
    0.53
    piew
    0.51
     being
    0.50
    Act Density 0.108%

    No Known Activations