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

    Neuronpedia

    INDEX
    Explanations

    patterns in mathematical equations or technical specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    "]
    -0.71
     Riv
    -0.68
    ']
    -0.67
    ̯
    -0.65
    '>
    -0.64
    millan
    -0.64
    "],
    -0.63
     cut
    -0.63
     nac
    -0.61
    shmi
    -0.61
    POSITIVE LOGITS
    .&
    1.27
    .$
    1.19
     avoient
    1.17
     Monfieur
    1.15
    .?
    1.13
    .\
    1.10
    ."
    1.09
     étoit
    1.09
    .<
    1.09
    .!
    1.07
    Act Density 0.227%

    No Known Activations