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

    Neuronpedia

    INDEX
    Explanations

    prefixes related to the concept of "re-" or actions that imply repetition, restoration, or reversal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    éľŀ
    -0.15
    amment
    -0.14
     magna
    -0.14
    añ
    -0.14
    meg
    -0.13
    ika
    -0.13
     Reed
    -0.13
    ingle
    -0.13
    uncio
    -0.13
    eed
    -0.13
    POSITIVE LOGITS
    imag
    0.25
    -env
    0.23
    inv
    0.23
    thinking
    0.23
    orient
    0.21
     inv
    0.21
    config
    0.20
    def
    0.20
     orient
    0.20
    env
    0.19
    Act Density 0.027%

    No Known Activations