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

    Neuronpedia

    INDEX
    Explanations

    information regarding statistics and data

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     shenan
    -1.81
     intersper
    -1.69
     unspeak
    -1.67
     reluct
    -1.64
     disreg
    -1.59
     impra
    -1.56
     indestru
    -1.55
     sophistic
    -1.54
     impractica
    -1.51
     maneu
    -1.50
    POSITIVE LOGITS
     alkoh
    0.82
     kokos
    0.81
     poliuret
    0.80
     pól
    0.80
     adverten
    0.78
     minimalis
    0.74
     silikon
    0.74
     bunda
    0.74
     trö
    0.73
     karton
    0.73
    Act Density 0.112%

    No Known Activations