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

    Neuronpedia

    INDEX
    Explanations

    references to actions or functions related to swapping or changing items

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

    swapping or switching

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     صوتيه
    -0.65
     Infórmanos
    -0.51
     ویکی‌پدی
    -0.49
     fopen
    -0.47
    AddTagHelper
    -0.47
    AutoField
    -0.45
    mutual
    -0.43
     unknownFields
    -0.43
    fromCharCode
    -0.43
     ***!
    -0.43
    POSITIVE LOGITS
     swapping
    0.53
     switching
    0.53
     Switching
    0.50
     intercamb
    0.50
    Switching
    0.49
     Swap
    0.49
     substituting
    0.48
     swapped
    0.48
     substituted
    0.48
    替换
    0.46
    Act Density 0.005%

    No Known Activations