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

    Neuronpedia

    INDEX
    Explanations

    references to relationships and interpersonal dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lew
    -0.16
     Shaw
    -0.15
    usto
    -0.15
    dÄĽl
    -0.15
     McCart
    -0.15
    vd
    -0.14
    çĢ
    -0.14
    бÑĢа
    -0.14
    e
    -0.14
    eve
    -0.13
    POSITIVE LOGITS
     rằng
    0.17
    ©
    0.17
    ä¸įè¦ģ
    0.17
     about
    0.16
    storybook
    0.15
    _about
    0.15
    about
    0.15
     jadx
    0.15
    جاÙĨ
    0.15
     stories
    0.14
    Act Density 0.058%

    No Known Activations