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

    Neuronpedia

    INDEX
    Explanations

    instances of personal anecdotes and experiences related to gender roles and responsibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Essentially
    -0.59
     Essentially
    -0.56
    HandlerContext
    -0.54
     SEDS
    -0.53
     essentially
    -0.52
    Datuak
    -0.52
    GEBURTS
    -0.51
     transcendent
    -0.51
     getField
    -0.51
    amaño
    -0.50
    POSITIVE LOGITS
     InputDecoration
    0.70
    Kjelder
    0.60
    🙆
    0.58
     foolish
    0.53
     nonsense
    0.53
    Jereo
    0.52
    nonsense
    0.51
    期刊论文
    0.51
     foolishness
    0.51
    🚶
    0.50
    Act Density 0.113%

    No Known Activations