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

    Neuronpedia

    INDEX
    Explanations

    key terms related to educational concepts and assessments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilik
    -0.17
    osti
    -0.15
    inheritdoc
    -0.15
    bish
    -0.15
    _mex
    -0.15
    pond
    -0.14
    aka
    -0.14
    廳
    -0.14
     xlink
    -0.14
    illing
    -0.14
    POSITIVE LOGITS
     vault
    0.17
     æĪ
    0.16
    kers
    0.16
    hang
    0.16
     hang
    0.16
    ker
    0.15
     flirt
    0.15
     protest
    0.15
     Stock
    0.15
     sm
    0.14
    Act Density 0.029%

    No Known Activations