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

    Neuronpedia

    INDEX
    Explanations

    numerical values or percentages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mil
    -0.18
    mil
    -0.18
    efa
    -0.15
    lip
    -0.15
    riendly
    -0.14
    edi
    -0.14
     kos
    -0.14
    imed
    -0.14
     Nich
    -0.14
    .hw
    -0.14
    POSITIVE LOGITS
     depending
    0.24
    depending
    0.21
    Insets
    0.17
    RTL
    0.17
    opus
    0.17
    ierz
    0.16
    contrast
    0.15
     Depending
    0.15
    iola
    0.15
    orsk
    0.15
    Act Density 0.047%

    No Known Activations