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

    Neuronpedia

    INDEX
    Explanations

    technical terms and keywords related to software development and data configurations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     im
    -0.59
     la
    -0.58
     los
    -0.57
     din
    -0.55
     des
    -0.55
     '
    -0.55
     de
    -0.54
     ‘
    -0.54
     lo
    -0.53
     sa
    -0.51
    POSITIVE LOGITS
     Monfieur
    1.30
     Efq
    1.17
     myſelf
    1.16
     itſelf
    1.10
     Majefty
    1.10
     poffe
    1.08
     becauſe
    1.07
     uſed
    1.07
     poffible
    1.06
     Theſe
    1.05
    Act Density 1.154%

    No Known Activations