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

    Neuronpedia

    INDEX
    Explanations

    references to examinations or evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kest
    -0.18
    reshold
    -0.18
    osal
    -0.15
    ÌĨ
    -0.15
    ATERIAL
    -0.15
     diplom
    -0.15
    cent
    -0.15
    ustum
    -0.15
    olib
    -0.15
    259
    -0.14
    POSITIVE LOGITS
    ered
    0.16
    pto
    0.16
    lists
    0.15
    bay
    0.14
    chai
    0.14
    bones
    0.14
    ãĥ³ãĥĩãĤ£
    0.14
     kop
    0.14
    SelfPermission
    0.14
    ĥ
    0.13
    Act Density 0.045%

    No Known Activations