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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a focus on the effects or impacts of something

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

    effect of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ChildScrollView
    -0.48
    "/",
    -0.47
    ViewFeatures
    -0.41
    AsUp
    -0.40
     Palacios
    -0.40
     Samuels
    -0.37
     Carrington
    -0.37
     Osborn
    -0.36
     Ellison
    -0.36
    eronau
    -0.36
    POSITIVE LOGITS
    Effects
    0.79
    effect
    0.77
     Effect
    0.77
     Effects
    0.73
    effects
    0.73
    Effect
    0.69
     effects
    0.69
     effect
    0.66
     effets
    0.63
     EFFECTS
    0.61
    Act Density 0.035%

    No Known Activations