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

    Neuronpedia

    INDEX
    Explanations

    URL links in HTML format

    oai_token-act-pair · gpt-3.5-turbo

    HTML attributes in hyperlinks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     equivalents
    -0.82
     scattering
    -0.68
     hoard
    -0.68
     MFT
    -0.68
     hardened
    -0.67
     Bees
    -0.66
     Bang
    -0.66
     endings
    -0.65
     BP
    -0.65
     Apprentice
    -0.65
    POSITIVE LOGITS
    https
    1.56
    http
    1.49
    javascript
    1.23
    <?
    1.23
    {{
    1.19
    //
    1.19
    "><
    1.17
    true
    1.14
    ">
    1.11
    false
    1.09
    Act Density 0.014%

    No Known Activations