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

    Neuronpedia

    INDEX
    Explanations

    numerical sequences mixed with special characters

    oai_token-act-pair · gpt-3.5-turbo

    repetitions of the number five

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hort
    -0.72
    icone
    -0.65
    Reviewer
    -0.59
    ãģ®å®
    -0.59
     Assange
    -0.58
    pty
    -0.57
    âĹ¼
    -0.57
    iasis
    -0.57
     Shinra
    -0.57
    ĸļ
    -0.57
    POSITIVE LOGITS
    Thirty
    0.95
    010
    0.85
    th
    0.84
    anging
    0.83
    âĺħ
    0.82
    âĢ³
    0.81
    43
    0.80
    678
    0.79
    âĢ²
    0.78
    42
    0.78
    Act Density 0.075%

    No Known Activations