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

    Neuronpedia

    INDEX
    Explanations

    phrases related to recommendations or suggestions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Normdatei
    -0.93
    PreferredItem
    -0.80
     Jop
    -0.74
     intptr
    -0.74
     famí
    -0.72
    DockStyle
    -0.71
     QtWidgets
    -0.71
    InitVars
    -0.70
     Elba
    -0.69
    DotNetBar
    -0.69
    POSITIVE LOGITS
    igay
    0.67
    appcompat
    0.65
     Uru
    0.65
     Gij
    0.64
    发表于
    0.64
     Avid
    0.63
     punct
    0.62
    שע
    0.61
    Identific
    0.60
     meiner
    0.60
    Act Density 0.022%

    No Known Activations