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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the effects and impact of various actions or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Jeografia
    -0.51
     Unburied
    -0.50
    ſelves
    -0.49
    AsUp
    -0.48
     dignité
    -0.48
     enfans
    -0.48
     femininas
    -0.48
     jongen
    -0.47
     debout
    -0.47
    ChildScrollView
    -0.46
    POSITIVE LOGITS
    effect
    1.38
     effect
    1.34
    Effect
    1.29
     effects
    1.29
     Effect
    1.27
    effects
    1.26
     Effects
    1.20
    Effects
    1.20
    ffect
    1.10
     affect
    1.05
    Act Density 0.200%

    No Known Activations