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

    Neuronpedia

    INDEX
    Explanations

    references to software modules and their configurations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Goodrich
    -0.51
    </b>
    -0.43
    s
    -0.42
    <b>
    -0.39
    (");
    -0.38
    Getty
    -0.38
    –
    -0.36
     Úl
    -0.36
     besten
    -0.36
    Bian
    -0.36
    POSITIVE LOGITS
     Module
    2.06
     module
    1.98
     Modules
    1.91
    module
    1.85
    Module
    1.84
     modules
    1.84
     MODULE
    1.74
    MODULE
    1.67
    modules
    1.59
    Modules
    1.58
    Act Density 0.078%

    No Known Activations