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

    Neuronpedia

    INDEX
    Explanations

    references to collective identity or community ownership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orous
    -0.16
    ood
    -0.16
    urs
    -0.14
    offs
    -0.14
    ilation
    -0.14
    оÑĩ
    -0.14
     us
    -0.14
    625
    -0.14
    .us
    -0.14
    ernal
    -0.13
    POSITIVE LOGITS
     own
    0.19
    chs
    0.17
    eah
    0.15
    SEL
    0.15
    bservice
    0.15
    bsp
    0.15
     behalf
    0.15
    self
    0.15
    brtc
    0.14
    icker
    0.14
    Act Density 0.154%

    No Known Activations