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

    Neuronpedia

    INDEX
    Explanations

    word forms that indicate possession or relational attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avra
    -0.16
     sĩ
    -0.15
    772
    -0.15
    ronym
    -0.15
    parator
    -0.14
    IGIN
    -0.14
    hdl
    -0.14
    336
    -0.13
    igin
    -0.13
    emple
    -0.13
    POSITIVE LOGITS
     ultimately
    0.19
     outcome
    0.18
     success
    0.17
     Ultimately
    0.17
     result
    0.16
     ultimate
    0.16
     succeed
    0.16
     final
    0.15
     Disaster
    0.15
    âĶIJ
    0.15
    Act Density 0.005%

    No Known Activations