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

    Neuronpedia

    INDEX
    Explanations

    references to issues related to reputation and image

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Payne
    -0.14
    *size
    -0.14
    ãĥ¼ãĤ¯
    -0.14
     Ownership
    -0.14
    resh
    -0.13
    etimes
    -0.13
    islav
    -0.13
    _codegen
    -0.13
    виÑĤ
    -0.13
    ÅĻÃŃž
    -0.13
    POSITIVE LOGITS
     reputation
    0.75
     reput
    0.64
     Reputation
    0.60
     image
    0.53
     credibility
    0.43
     standing
    0.42
    image
    0.41
     Image
    0.39
     prestige
    0.37
    -image
    0.36
    Act Density 0.064%

    No Known Activations