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

    Neuronpedia

    INDEX
    Explanations

    mentions of future events or plans

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Wtf
    -0.54
     Whence
    -0.53
     Miscell
    -0.51
     ducato
    -0.50
     unspeak
    -0.50
     forskj
    -0.50
    érard
    -0.49
     betreffende
    -0.49
     triomphe
    -0.48
     veiligheid
    -0.47
    POSITIVE LOGITS
     ideolog
    0.76
     bej
    0.71
     intende
    0.70
     diabe
    0.69
     notor
    0.68
     republi
    0.68
    atify
    0.67
     solidar
    0.65
     ambul
    0.63
     gambe
    0.63
    Act Density 0.201%

    No Known Activations