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

    Neuronpedia

    INDEX
    Explanations

    terms related to revolution and change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ög
    -0.16
    uning
    -0.16
     éĹ
    -0.15
    ีà¹ī
    -0.15
    wend
    -0.15
    elik
    -0.14
    ebra
    -0.14
    edian
    -0.14
    ži
    -0.14
    eria
    -0.14
    POSITIVE LOGITS
    ival
    0.31
    olutions
    0.31
    olver
    0.28
    olution
    0.28
    amped
    0.28
    iving
    0.26
    olving
    0.26
    ital
    0.26
    ived
    0.25
    olt
    0.25
    Act Density 0.012%

    No Known Activations