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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating existence or possession

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     acos
    -0.16
    cke
    -0.14
    ason
    -0.14
    üm
    -0.14
    )prepare
    -0.14
    umpt
    -0.14
    ubo
    -0.13
    abra
    -0.13
    Ĥ
    -0.13
    uding
    -0.13
    POSITIVE LOGITS
    رÛĮÙħ
    0.14
    ãĥĭãĥ¼
    0.14
     Gaz
    0.14
    碼
    0.14
    nodoc
    0.14
    JNI
    0.13
    fr
    0.13
     jun
    0.13
    _globals
    0.13
    los
    0.13
    Act Density 0.554%

    No Known Activations