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

    Neuronpedia

    INDEX
    Explanations

    references to legal and political matters

    oai_token-act-pair · gpt-3.5-turbo

    references to violence or death

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bia
    -0.57
     Prix
    -0.54
     CPUs
    -0.54
     occult
    -0.54
     ("
    -0.53
     Biblical
    -0.50
    owered
    -0.49
     Neo
    -0.49
    iga
    -0.49
     aka
    -0.49
    POSITIVE LOGITS
    %"
    1.00
    [/
    0.99
    ?'
    0.81
     [
    0.80
    displayText
    0.80
    */(
    0.79
    ,''
    0.77
     âĢ
    0.76
    .""
    0.75
    ?"
    0.75
    Act Density 0.975%

    No Known Activations