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

    Neuronpedia

    INDEX
    Explanations

    specific character codes or symbols commonly used in digital communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     comprom
    -0.14
    è¦ģæ±Ĥ
    -0.13
     sacrific
    -0.13
    .reject
    -0.12
     požadav
    -0.12
     odmÃŃt
    -0.12
     оÑĤказ
    -0.12
    reject
    -0.12
    emand
    -0.12
    optimized
    -0.12
    POSITIVE LOGITS
     apparently
    0.26
     occasionally
    0.24
     later
    0.23
     mention
    0.23
     coinc
    0.22
     oddly
    0.22
     strangely
    0.22
     mentioned
    0.22
     seemingly
    0.22
     vaguely
    0.22
    Act Density 0.455%

    No Known Activations