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

    Neuronpedia

    INDEX
    Explanations

    names of locations and entities involved in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DAQ
    -0.14
    orest
    -0.14
    icated
    -0.14
     latter
    -0.14
    umeric
    -0.13
    efined
    -0.13
    ishes
    -0.13
    ãĥ³ãĥĦ
    -0.13
    igits
    -0.13
     Murder
    -0.13
    POSITIVE LOGITS
    odore
    0.23
    atre
    0.22
    adays
    0.19
    $MESS
    0.17
     Willi
    0.16
    atomy
    0.14
    ainen
    0.14
    vron
    0.14
    mé
    0.14
    etheless
    0.14
    Act Density 0.065%

    No Known Activations