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

    Neuronpedia

    INDEX
    Explanations

    quantitative metrics or evaluations related to performance and improvement in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CascadeType
    -0.57
    <?
    -0.57
     lest
    -0.54
     causing
    -0.51
     FANDOM
    -0.49
    ]")]
    -0.48
     afin
    -0.46
    )')
    -0.45
    ())));
    -0.45
     supaya
    -0.43
    POSITIVE LOGITS
     studying
    0.72
     AssemblyCompany
    0.71
     subscribing
    0.71
     playing
    0.70
     dzięki
    0.70
     practising
    0.69
    ValueStyle
    0.69
     practicing
    0.68
     doing
    0.68
     watching
    0.67
    Act Density 0.481%

    No Known Activations