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

    Neuronpedia

    INDEX
    Explanations

    references to cultural and social tropes related to gender and power dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ;element
    -0.17
    opus
    -0.16
    iple
    -0.16
    illis
    -0.15
    oin
    -0.15
    opup
    -0.14
     quar
    -0.14
    .mixin
    -0.14
    udio
    -0.14
    ClientRect
    -0.14
    POSITIVE LOGITS
     trop
    0.17
     narc
    0.14
    NetMessage
    0.14
     Sonic
    0.14
     leisure
    0.14
     white
    0.13
    encv
    0.13
     hóa
    0.13
     narratives
    0.13
     binaries
    0.13
    Act Density 0.374%

    No Known Activations