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

    Neuronpedia

    INDEX
    Explanations

    mentions of experimental conditions related to control groups in scientific studies

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     useRouter
    -0.76
    WriteLiteral
    -0.75
     Majefty
    -0.74
    SPATH
    -0.71
     Escolar
    -0.71
     itſelf
    -0.71
     Nashville
    -0.70
    izarse
    -0.69
    isLoaded
    -0.68
    avais
    -0.67
    POSITIVE LOGITS
     Sham
    1.39
    Sham
    1.27
     sham
    1.16
    sham
    0.86
    numerusform
    0.67
    setVerticalGroup
    0.66
     kee
    0.60
     pam
    0.57
    Enciclopedia
    0.53
     defaultstate
    0.52
    Act Density 0.001%

    No Known Activations