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

    Neuronpedia

    INDEX
    Explanations

    references to hash functions and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     <
    -0.57
     gonna
    -0.49
    apiKey
    -0.49
     
    -0.48
    бя
    -0.48
     aus
    -0.48
    <eos>
    -0.47
     let
    -0.46
     Aber
    -0.46
     ©
    -0.46
    POSITIVE LOGITS
     raiſ
    0.99
     незавершена
    0.95
     Efq
    0.93
    %%%%%%%%%%%%%%%%
    0.93
     fhew
    0.93
     Jefus
    0.92
     propOrder
    0.92
     caufe
    0.91
     uſe
    0.91
     iſt
    0.88
    Act Density 0.135%

    No Known Activations