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

    Neuronpedia

    INDEX
    Explanations

    instances of expressions indicating surprise or unexpected events

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

    when/if followed by pronoun or article

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     enfans
    -0.59
     propOrder
    -0.49
    AddTagHelper
    -0.49
    LocationManager
    -0.48
    MemoryWarning
    -0.47
     Terraria
    -0.47
    ſelf
    -0.44
    complexType
    -0.44
    rizona
    -0.43
     UITextField
    -0.41
    POSITIVE LOGITS
    IMPORTED
    0.56
     اینکه
    0.52
     برانيه
    0.47
     people
    0.43
    irov
    0.42
     borboleta
    0.42
    ۜ
    0.41
     بگ
    0.41
     freckles
    0.40
     mutiara
    0.39
    Act Density 0.022%

    No Known Activations