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

    Neuronpedia

    INDEX
    Explanations

    specific terms related to entertainment and content classification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Edgar
    -0.16
     Hamp
    -0.15
    frauen
    -0.14
    abox
    -0.14
    ÙĬدÙĬ
    -0.14
    ami
    -0.14
    regor
    -0.14
    illis
    -0.14
    éļ¨
    -0.14
    azen
    -0.13
    POSITIVE LOGITS
     Gall
    0.16
     patches
    0.14
     grap
    0.14
    αÏģ
    0.14
    erin
    0.14
     Cust
    0.14
    maz
    0.14
    rios
    0.13
    237
    0.13
    веÑģÑĤ
    0.13
    Act Density 0.014%

    No Known Activations