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

    Neuronpedia

    INDEX
    Explanations

    sentences that contain significant figures or roles related to leadership and contributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pear
    -0.16
    áb
    -0.16
    \Carbon
    -0.15
    оваÑĢи
    -0.15
    .shtml
    -0.15
     seedu
    -0.14
     Sabha
    -0.14
    antz
    -0.13
    vla
    -0.13
    ripp
    -0.13
    POSITIVE LOGITS
     himself
    0.18
     who
    0.17
    åħ¸
    0.16
    geb
    0.16
     whom
    0.16
     twin
    0.14
    opor
    0.14
    gın
    0.14
     lifelong
    0.14
    who
    0.14
    Act Density 0.098%

    No Known Activations