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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and titles of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bancada
    -0.39
     justement
    -0.39
     effectivement
    -0.38
    Бахар
    -0.38
     vinos
    -0.38
     Allerdings
    -0.36
     IIRC
    -0.36
     Stimmung
    -0.35
     precisamente
    -0.35
     jā
    -0.34
    POSITIVE LOGITS
     beloved
    0.96
    Beloved
    0.88
     Beloved
    0.86
     died
    0.85
     Passed
    0.80
     formerly
    0.76
     passed
    0.73
     peacefully
    0.73
     loving
    0.71
     äls
    0.70
    Act Density 0.072%

    No Known Activations