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

    Neuronpedia

    INDEX
    Explanations

    references to levels of expertise, skill, or grading in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    punk
    -0.16
    ÛĮرÛĮ
    -0.15
    ulative
    -0.15
    BlockSize
    -0.14
    erti
    -0.14
    oco
    -0.14
    ovnÄĽ
    -0.14
    /feed
    -0.13
     паÑģ
    -0.13
     coalition
    -0.13
    POSITIVE LOGITS
    ouri
    0.17
    tn
    0.17
    ýš
    0.16
     Picker
    0.15
     Sokol
    0.15
     Hud
    0.14
     ex
    0.14
    incinn
    0.14
    .experimental
    0.14
    292
    0.14
    Act Density 0.028%

    No Known Activations