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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate contrasts or differences in comparison

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    {#
    -0.61
     hereby
    -0.59
    setDo
    -0.58
     bezeichneter
    -0.55
    astify
    -0.55
     урна
    -0.55
    centerline
    -0.54
    gev
    -0.54
     bénéfices
    -0.53
     muſt
    -0.53
    POSITIVE LOGITS
    unlike
    1.58
     unlike
    1.56
    Unlike
    1.50
     Unlike
    1.46
    lihood
    1.01
     Gegensatz
    0.88
    Whereas
    0.85
    Contrary
    0.83
     contrário
    0.80
    DockStyle
    0.79
    Act Density 0.105%

    No Known Activations