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

    Neuronpedia

    INDEX
    Explanations

    words related to obligation, accountability, and inquiry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SingleNode
    -0.15
    ktop
    -0.15
    pole
    -0.15
    ¨ë¶Ģ
    -0.15
    AXB
    -0.15
    tober
    -0.15
    ÃŃž
    -0.15
    isini
    -0.15
    oler
    -0.14
    ä¹³
    -0.14
    POSITIVE LOGITS
     Bee
    0.18
    orch
    0.17
     responsible
    0.17
     Responsible
    0.17
    @qq
    0.15
    arra
    0.15
     Weather
    0.14
     Hutchinson
    0.14
    bob
    0.14
     compared
    0.14
    Act Density 0.001%

    No Known Activations