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

    Neuronpedia

    INDEX
    Explanations

    references to specific animals and their classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ativos
    -0.36
    izados
    -0.33
    nicos
    -0.32
    idos
    -0.29
     ceux
    -0.29
    ificados
    -0.29
    ivos
    -0.29
     diversos
    -0.27
     ellos
    -0.27
    uestos
    -0.26
    POSITIVE LOGITS
    las
    0.54
    Las
    0.52
     Las
    0.52
     las
    0.50
    LAS
    0.44
     LAS
    0.44
    adas
    0.44
    áticas
    0.44
    ativas
    0.42
     delle
    0.40
    Act Density 0.116%

    No Known Activations