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

    Neuronpedia

    INDEX
    Explanations

    relationships relating to ownership and specificity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    swick
    -0.15
    lez
    -0.15
    rox
    -0.15
    оÑĢод
    -0.14
    VERS
    -0.14
    DELAY
    -0.14
    оÑģÑĤ
    -0.14
    Ỽp
    -0.14
    IOR
    -0.14
    .bc
    -0.14
    POSITIVE LOGITS
     own
    0.25
     certain
    0.24
     different
    0.22
     ways
    0.21
     specific
    0.21
     unique
    0.21
    ä¸įåIJĮçļĦ
    0.21
    èĩªå·±çļĦ
    0.20
    Certain
    0.19
     corresponding
    0.19
    Act Density 0.153%

    No Known Activations