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

    Neuronpedia

    INDEX
    Explanations

    phrases related to viewpoints and perspectives in discussions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     sumo
    -0.52
     charité
    -0.51
    Care
    -0.48
    netbeans
    -0.47
     cytok
    -0.47
     république
    -0.47
     disulfide
    -0.47
     Sov
    -0.46
    Alt
    -0.46
     Muro
    -0.45
    POSITIVE LOGITS
     AssemblyTitle
    1.02
    }")
    1.02
    ]").
    0.99
    ViewFeatures
    0.87
    "])
    0.85
     AspNetCore
    0.84
    '])
    0.84
    "]).
    0.84
     })
    0.82
    "]),
    0.82
    Act Density 0.088%

    No Known Activations