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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a point in time or a condition that needs to be met

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    FTFY
    -0.81
     disreg
    -0.77
    YMMV
    -0.69
     impra
    -0.69
    Noice
    -0.68
     unspeak
    -0.66
     subgoal
    -0.65
     ftw
    -0.65
     prolly
    -0.64
     indescri
    -0.64
    POSITIVE LOGITS
     masaj
    0.82
     susun
    0.81
     umo
    0.76
     CiNii
    0.75
     thuy
    0.75
     lele
    0.73
     granada
    0.72
     mariscos
    0.69
     uhr
    0.69
     nuoc
    0.69
    Act Density 0.320%

    No Known Activations