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

    Neuronpedia

    INDEX
    Explanations

    titles of music tracks or other content

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     nodd
    -0.62
    Ire
    -0.59
     notor
    -0.58
     destro
    -0.56
    STDOUT
    -0.55
    blance
    -0.54
     proport
    -0.54
     undermin
    -0.54
     condem
    -0.54
     confir
    -0.54
    POSITIVE LOGITS
     ->
    0.84
     |
    0.78
     [/
    0.73
    ↵
    0.71
     [-
    0.70
     |--
    0.70
     ·
    0.69
     -->
    0.69
     =================================
    0.69
     âĻ
    0.69
    Act Density 0.752%

    No Known Activations