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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate attributes or descriptions related to quality and categorization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    438
    -0.15
    ingham
    -0.15
    eward
    -0.13
    æĬķ注
    -0.12
    ennes
    -0.12
    623
    -0.12
    ’n
    -0.12
    ÑĨен
    -0.12
    anyahu
    -0.12
    uppet
    -0.12
    POSITIVE LOGITS
    pcl
    0.15
    -Sah
    0.13
    WRAPPER
    0.13
     StringComparison
    0.13
    lili
    0.12
    .shows
    0.12
    elere
    0.12
    )((((
    0.12
    ladu
    0.12
    .synthetic
    0.12
    Act Density 0.148%

    No Known Activations