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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal opinions and feelings towards ideas or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    don't care what others think

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ölkerung
    -0.55
    principalColumn
    -0.55
     Wicidata
    -0.47
     HFILL
    -0.46
    corazón
    -0.46
     resourceCulture
    -0.45
    URLException
    -0.45
    存于互联网档案馆
    -0.44
    unteer
    -0.44
    árbol
    -0.43
    POSITIVE LOGITS
     electronic
    0.39
     unrealistic
    0.38
     FICTION
    0.37
     artificial
    0.37
     silly
    0.36
    ]})
    0.36
    }))
    0.35
    ✭
    0.34
     Drapeau
    0.34
     invalid
    0.34
    Act Density 0.124%

    No Known Activations