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

    Neuronpedia

    INDEX
    Explanations

    phrases related to statistics and assessments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    課
    -0.15
     states
    -0.14
    dech
    -0.14
    antz
    -0.14
    ÏĥÏĥ
    -0.14
     States
    -0.14
    ogne
    -0.14
    states
    -0.13
     unstable
    -0.13
    abase
    -0.13
    POSITIVE LOGITS
     disabled
    0.19
    disabled
    0.18
     Disabled
    0.18
    Disabled
    0.17
    Leaf
    0.16
    -disabled
    0.15
    #__
    0.15
    ارا
    0.15
     Disability
    0.15
     DISABLE
    0.15
    Act Density 0.000%

    No Known Activations