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

    Neuronpedia

    INDEX
    Explanations

    repetitive phrases or similarities in text

    oai_token-act-pair · gpt-3.5-turbo

    the repetition of the word "same."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ľ
    -0.81
    å§
    -0.78
    irtual
    -0.73
    HCR
    -0.72
    ä¿
    -0.69
    better
    -0.67
    amar
    -0.67
    éģ
    -0.65
    ¿
    -0.65
    Ķ
    -0.65
    POSITIVE LOGITS
     thing
    1.20
     exact
    1.16
     amount
    0.97
     sized
    0.95
     guy
    0.95
     wording
    0.95
     size
    0.92
     principle
    0.92
     name
    0.92
     result
    0.92
    Act Density 0.039%

    No Known Activations