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

    Neuronpedia

    INDEX
    Explanations

    references to coffee and cafes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tanleria
    -0.69
    ագրություններ
    -0.61
     Maul
    -0.59
    FACTOR
    -0.57
    inados
    -0.57
    DataMember
    -0.57
    glEnd
    -0.55
    Acceso
    -0.55
    anyahu
    -0.54
    Reds
    -0.53
    POSITIVE LOGITS
     Coffee
    1.05
     COFFEE
    0.97
    Coffee
    0.96
     coffee
    0.96
    coffee
    0.89
     confusion
    0.82
    Café
    0.81
     Kaffee
    0.80
     Café
    0.79
    ☕️
    0.78
    Act Density 0.037%

    No Known Activations