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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the degree and impact of effects

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

    effect on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    msgTypes
    -0.45
    wijs
    -0.34
     interchangeably
    -0.33
    代わりに
    -0.33
    exitRule
    -0.33
    AnchorTagHelper
    -0.33
    дох
    -0.33
     Erzb
    -0.33
     zichzelf
    -0.32
    pondre
    -0.32
    POSITIVE LOGITS
     effects
    1.27
     effect
    1.20
    effects
    1.15
     impact
    1.13
    Effects
    1.11
    effect
    1.10
     Effects
    1.05
     impacts
    1.00
     EFFECTS
    1.00
    Effect
    0.98
    Act Density 0.183%

    No Known Activations