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

    Neuronpedia

    INDEX
    Explanations

    names of places and objects in Spanish

    oai_token-act-pair · gpt-3.5-turbo

    plural nouns in Spanish

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ONY
    -0.81
    akery
    -0.79
    ISM
    -0.79
    ously
    -0.76
    ANK
    -0.76
    ISON
    -0.74
    ller
    -0.73
    atum
    -0.73
    erity
    -0.73
    fare
    -0.72
    POSITIVE LOGITS
     dos
    0.91
     los
    0.84
    omething
    0.84
     redes
    0.83
     Padres
    0.74
     princip
    0.71
    ources
    0.69
    essions
    0.68
     mu
    0.68
     li
    0.67
    Act Density 0.042%

    No Known Activations