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

    Neuronpedia

    INDEX
    Explanations

    Twitter handles and links

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     BoxDecoration
    -0.99
    abestanden
    -0.86
    PreferredItem
    -0.78
    webElement
    -0.76
    SequentialGroup
    -0.76
    ^(@)
    -0.72
     ―――――
    -0.71
     defaultstate
    -0.70
    UnsafeEnabled
    -0.70
    ?')
    -0.70
    POSITIVE LOGITS
     @
    0.96
    @
    0.92
     (@
    0.90
    (@
    0.72
    enumi
    0.70
    büro
    0.61
    /@
    0.57
    -@
    0.55
    #!/
    0.53
     cauza
    0.52
    Act Density 0.155%

    No Known Activations