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

    Neuronpedia

    INDEX
    Explanations

    phrases and concepts related to social justice and activism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     reaſon
    -0.73
    WriteTagHelper
    -0.71
    setVerticalGroup
    -0.69
     uſe
    -0.69
    ]--;
    -0.69
     myſelf
    -0.66
    SharedDtor
    -0.66
     Monfieur
    -0.65
     chofe
    -0.64
     lắm
    -0.64
    POSITIVE LOGITS
     would
    0.69
     is
    0.63
    sidemargin
    0.59
     wouldn
    0.55
     isn
    0.55
     or
    0.54
     can
    0.54
     may
    0.53
    would
    0.52
     makes
    0.51
    Act Density 0.721%

    No Known Activations