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

    Neuronpedia

    INDEX
    Explanations

    instances of repetition or similarity in language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    JKLMNOP
    -0.17
    oure
    -0.15
    quo
    -0.14
    AFP
    -0.14
    oux
    -0.14
    ::$_
    -0.14
    'gc
    -0.14
    oul
    -0.14
    .azure
    -0.13
    ila
    -0.13
    POSITIVE LOGITS
     previous
    0.27
     previously
    0.25
     earlier
    0.23
    .previous
    0.21
    previous
    0.21
     Previously
    0.21
     regular
    0.20
     Previous
    0.20
     normal
    0.19
     usual
    0.18
    Act Density 0.147%

    No Known Activations