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

    Neuronpedia

    INDEX
    Explanations

    verbs and phrases indicating states of being or experiences related to suffering and support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.80
    Demografía
    -0.77
    )");
    -0.67
     preocupes
    -0.65
     &___
    -0.62
     maaaring
    -0.61
    cinogenicity
    -0.58
    ArgumentParser
    -0.58
    binaan
    -0.58
     sonst
    -0.57
    POSITIVE LOGITS
    unchecked
    0.58
     knowing
    0.48
     ilman
    0.48
    armed
    0.47
     equipped
    0.46
     ControllerBase
    0.46
    一身
    0.46
    Armed
    0.45
     fresh
    0.45
     without
    0.43
    Act Density 0.217%

    No Known Activations