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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating possession or attribution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    someone
    -0.16
     somebody
    -0.16
    ekl
    -0.16
     something
    -0.16
    weis
    -0.16
     someone
    -0.15
    something
    -0.15
    AMA
    -0.14
    ;element
    -0.14
    ceae
    -0.14
    POSITIVE LOGITS
     a
    0.36
    	a
    0.24
    _a
    0.24
    a
    0.21
    а
    0.17
    "a
    0.17
    >a
    0.17
    )a
    0.17
    -a
    0.17
    ,a
    0.16
    Act Density 0.113%

    No Known Activations