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

    Neuronpedia

    INDEX
    Explanations

    references to collective identity or community, particularly regarding shared beliefs or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itself
    -0.16
    YC
    -0.14
     Sirius
    -0.14
     Herbal
    -0.14
    wort
    -0.14
    zar
    -0.14
    alia
    -0.14
     verg
    -0.14
     pg
    -0.14
    ober
    -0.14
    POSITIVE LOGITS
    rollo
    0.18
    agem
    0.16
    igm
    0.16
    lds
    0.15
    enal
    0.14
    еÑİ
    0.13
    929
    0.13
    838
    0.13
    anes
    0.13
    itution
    0.13
    Act Density 0.042%

    No Known Activations