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

    Neuronpedia

    INDEX
    Explanations

    pronouns and phrases indicating possession or relation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hill
    -0.17
     cue
    -0.15
    ä¿Ĺ
    -0.15
    adapter
    -0.14
    /pdf
    -0.14
     clue
    -0.14
    ly
    -0.14
    repid
    -0.13
    berger
    -0.13
    andr
    -0.13
    POSITIVE LOGITS
    okable
    0.17
    AGMA
    0.15
    ARSE
    0.15
     оÑĦоÑĢм
    0.15
    aversal
    0.15
    ecs
    0.14
    chu
    0.14
    /Dk
    0.14
     interrogation
    0.14
    _ALLOC
    0.13
    Act Density 0.002%

    No Known Activations